Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 104 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2739. Min Range: -6.2739
Max Act: 6.2739. Min Act: -0.1700
Data Index: 1278657 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2739. Min Range: -6.2739
Max Act: 6.2739. Min Act: -0.1700
Data Index: 7813703 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2739. Min Range: -6.2739
Max Act: 6.2114. Min Act: -0.1700
Data Index: 1449655 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2739. Min Range: -6.2739
Max Act: 6.1489. Min Act: -0.1700
Data Index: 4864790 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2739. Min Range: -6.2739
Max Act: 6.1177. Min Act: -0.1700
Data Index: 5613176 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2739. Min Range: -6.2739
Max Act: 5.8989. Min Act: -0.1700
Data Index: 1231628 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2739. Min Range: -6.2739
Max Act: 5.8989. Min Act: -0.1700
Data Index: 3118598 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2739. Min Range: -6.2739
Max Act: 5.8677. Min Act: -0.1700
Data Index: 4234019 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2739. Min Range: -6.2739
Max Act: 5.8364. Min Act: -0.1700
Data Index: 6922131 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2739. Min Range: -6.2739
Max Act: 5.8364. Min Act: -0.1700
Data Index: 926259 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2739. Min Range: -6.2739
Max Act: 5.8364. Min Act: -0.1700
Data Index: 383865 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2739. Min Range: -6.2739
Max Act: 5.8052. Min Act: -0.1700
Data Index: 3386677 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2739. Min Range: -6.2739
Max Act: 5.8052. Min Act: -0.1700
Data Index: 2156804 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2739. Min Range: -6.2739
Max Act: 5.8052. Min Act: -0.1700
Data Index: 2394219 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2739. Min Range: -6.2739
Max Act: 5.8052. Min Act: -0.1700
Data Index: 3457041 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2739. Min Range: -6.2739
Max Act: 5.8364. Min Act: -0.1700
Data Index: 4992273 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2739. Min Range: -6.2739
Max Act: 5.8052. Min Act: -0.1700
Data Index: 4658316 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2739. Min Range: -6.2739
Max Act: 5.7739. Min Act: -0.1700
Data Index: 2703708 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2739. Min Range: -6.2739
Max Act: 5.7739. Min Act: -0.1700
Data Index: 595759 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2739. Min Range: -6.2739
Max Act: 5.7739. Min Act: -0.1700
Data Index: 3698356 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19