Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4408 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4742. Min Range: -2.4742
Max Act: 2.4742. Min Act: -0.1700
Data Index: 7944835 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4742. Min Range: -2.4742
Max Act: 2.4254. Min Act: -0.1700
Data Index: 2159043 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4742. Min Range: -2.4742
Max Act: 2.4254. Min Act: -0.1700
Data Index: 8208763 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4742. Min Range: -2.4742
Max Act: 2.3765. Min Act: -0.1700
Data Index: 5975941 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4742. Min Range: -2.4742
Max Act: 2.3601. Min Act: -0.1700
Data Index: 2843815 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4742. Min Range: -2.4742
Max Act: 2.3273. Min Act: -0.1700
Data Index: 1520643 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4742. Min Range: -2.4742
Max Act: 2.3109. Min Act: -0.1700
Data Index: 4502960 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4742. Min Range: -2.4742
Max Act: 2.3109. Min Act: -0.1700
Data Index: 8680927 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4742. Min Range: -2.4742
Max Act: 2.3109. Min Act: -0.1700
Data Index: 1013577 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4742. Min Range: -2.4742
Max Act: 2.3109. Min Act: -0.1700
Data Index: 710075 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4742. Min Range: -2.4742
Max Act: 2.2945. Min Act: -0.1700
Data Index: 5103268 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4742. Min Range: -2.4742
Max Act: 2.2945. Min Act: -0.1700
Data Index: 2408057 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4742. Min Range: -2.4742
Max Act: 2.2945. Min Act: -0.1700
Data Index: 1809895 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4742. Min Range: -2.4742
Max Act: 2.2780. Min Act: -0.1700
Data Index: 7797204 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4742. Min Range: -2.4742
Max Act: 2.2945. Min Act: -0.1700
Data Index: 4559078 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4742. Min Range: -2.4742
Max Act: 2.2780. Min Act: -0.1700
Data Index: 2101236 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4742. Min Range: -2.4742
Max Act: 2.2780. Min Act: -0.1700
Data Index: 5922753 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4742. Min Range: -2.4742
Max Act: 2.2945. Min Act: -0.1700
Data Index: 6492821 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4742. Min Range: -2.4742
Max Act: 2.2780. Min Act: -0.1700
Data Index: 8195346 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4742. Min Range: -2.4742
Max Act: 2.2615. Min Act: -0.1700
Data Index: 2267134 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19