Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2205 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9116. Min Range: -10.9116
Max Act: 10.9116. Min Act: -0.1700
Data Index: 2752752 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9116. Min Range: -10.9116
Max Act: 10.6616. Min Act: -0.1699
Data Index: 943292 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9116. Min Range: -10.9116
Max Act: 10.4741. Min Act: -0.1700
Data Index: 5459457 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9116. Min Range: -10.9116
Max Act: 10.4741. Min Act: -0.1698
Data Index: 8719596 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9116. Min Range: -10.9116
Max Act: 10.4741. Min Act: -0.1700
Data Index: 6363068 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9116. Min Range: -10.9116
Max Act: 10.4741. Min Act: -0.1700
Data Index: 1246316 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9116. Min Range: -10.9116
Max Act: 10.4116. Min Act: -0.1700
Data Index: 1433119 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9116. Min Range: -10.9116
Max Act: 10.4116. Min Act: -0.1700
Data Index: 2798952 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9116. Min Range: -10.9116
Max Act: 10.3491. Min Act: -0.1694
Data Index: 5677371 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9116. Min Range: -10.9116
Max Act: 10.2866. Min Act: -0.1700
Data Index: 6315936 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9116. Min Range: -10.9116
Max Act: 10.2866. Min Act: -0.1700
Data Index: 7875671 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9116. Min Range: -10.9116
Max Act: 10.3491. Min Act: -0.1697
Data Index: 8787654 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9116. Min Range: -10.9116
Max Act: 10.3491. Min Act: -0.1700
Data Index: 8122167 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9116. Min Range: -10.9116
Max Act: 10.3491. Min Act: -0.1700
Data Index: 5182167 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9116. Min Range: -10.9116
Max Act: 10.3491. Min Act: -0.1699
Data Index: 1085939 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9116. Min Range: -10.9116
Max Act: 10.2866. Min Act: -0.1700
Data Index: 1883735 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9116. Min Range: -10.9116
Max Act: 10.2241. Min Act: -0.1700
Data Index: 624128 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9116. Min Range: -10.9116
Max Act: 10.2866. Min Act: -0.1699
Data Index: 6220453 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9116. Min Range: -10.9116
Max Act: 10.2241. Min Act: -0.1699
Data Index: 1958612 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9116. Min Range: -10.9116
Max Act: 10.2866. Min Act: -0.1700
Data Index: 2773210 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19