Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3235 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8112. Min Range: -3.8112
Max Act: 3.8112. Min Act: -0.1700
Data Index: 5069075 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8112. Min Range: -3.8112
Max Act: 3.8112. Min Act: -0.1700
Data Index: 3735390 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8112. Min Range: -3.8112
Max Act: 3.7799. Min Act: -0.1700
Data Index: 4514774 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8112. Min Range: -3.8112
Max Act: 3.7487. Min Act: -0.1700
Data Index: 4171513 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8112. Min Range: -3.8112
Max Act: 3.7487. Min Act: -0.1700
Data Index: 8109360 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8112. Min Range: -3.8112
Max Act: 3.7487. Min Act: -0.1700
Data Index: 7122361 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8112. Min Range: -3.8112
Max Act: 3.7174. Min Act: -0.1700
Data Index: 2436700 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8112. Min Range: -3.8112
Max Act: 3.7174. Min Act: -0.1700
Data Index: 8512982 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8112. Min Range: -3.8112
Max Act: 3.7174. Min Act: -0.1700
Data Index: 8292533 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8112. Min Range: -3.8112
Max Act: 3.6861. Min Act: -0.1700
Data Index: 8418882 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8112. Min Range: -3.8112
Max Act: 3.6861. Min Act: -0.1700
Data Index: 3641939 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8112. Min Range: -3.8112
Max Act: 3.6861. Min Act: -0.1700
Data Index: 1798924 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8112. Min Range: -3.8112
Max Act: 3.6861. Min Act: -0.1700
Data Index: 3583868 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8112. Min Range: -3.8112
Max Act: 3.6548. Min Act: -0.1700
Data Index: 5906333 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8112. Min Range: -3.8112
Max Act: 3.6548. Min Act: -0.1700
Data Index: 5748824 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8112. Min Range: -3.8112
Max Act: 3.6548. Min Act: -0.1700
Data Index: 4802371 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8112. Min Range: -3.8112
Max Act: 3.6548. Min Act: -0.1700
Data Index: 2545179 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8112. Min Range: -3.8112
Max Act: 3.6548. Min Act: -0.1700
Data Index: 1020653 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8112. Min Range: -3.8112
Max Act: 3.6861. Min Act: -0.1700
Data Index: 7481167 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8112. Min Range: -3.8112
Max Act: 3.6235. Min Act: -0.1700
Data Index: 6035023 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19