Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6782. Min Range: -4.6782
Max Act: 4.6782. Min Act: -0.1700
Data Index: 6289840 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6782. Min Range: -4.6782
Max Act: 4.6470. Min Act: -0.1700
Data Index: 4863852 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6782. Min Range: -4.6782
Max Act: 4.4594. Min Act: -0.1700
Data Index: 221120 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6782. Min Range: -4.6782
Max Act: 4.4282. Min Act: -0.1700
Data Index: 4278212 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6782. Min Range: -4.6782
Max Act: 4.3657. Min Act: -0.1700
Data Index: 1894642 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6782. Min Range: -4.6782
Max Act: 4.3344. Min Act: -0.1700
Data Index: 1603230 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6782. Min Range: -4.6782
Max Act: 4.3344. Min Act: -0.1700
Data Index: 7208122 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6782. Min Range: -4.6782
Max Act: 4.3032. Min Act: -0.1700
Data Index: 7567432 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6782. Min Range: -4.6782
Max Act: 4.3032. Min Act: -0.1700
Data Index: 4187986 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6782. Min Range: -4.6782
Max Act: 4.2719. Min Act: -0.1700
Data Index: 6393955 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6782. Min Range: -4.6782
Max Act: 4.2719. Min Act: -0.1700
Data Index: 3964746 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6782. Min Range: -4.6782
Max Act: 4.2407. Min Act: -0.1700
Data Index: 6640447 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6782. Min Range: -4.6782
Max Act: 4.2407. Min Act: -0.1700
Data Index: 2786585 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6782. Min Range: -4.6782
Max Act: 4.2407. Min Act: -0.1700
Data Index: 1528632 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6782. Min Range: -4.6782
Max Act: 4.2407. Min Act: -0.1700
Data Index: 295750 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6782. Min Range: -4.6782
Max Act: 4.2094. Min Act: -0.1700
Data Index: 1908953 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6782. Min Range: -4.6782
Max Act: 4.2407. Min Act: -0.1700
Data Index: 4928961 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6782. Min Range: -4.6782
Max Act: 4.2094. Min Act: -0.1700
Data Index: 7791390 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6782. Min Range: -4.6782
Max Act: 4.2094. Min Act: -0.1700
Data Index: 1277139 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6782. Min Range: -4.6782
Max Act: 4.2094. Min Act: -0.1700
Data Index: 2486000 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19