Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4090 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5049. Min Range: -4.5049
Max Act: 4.5049. Min Act: -0.1700
Data Index: 8746775 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5049. Min Range: -4.5049
Max Act: 4.3487. Min Act: -0.1700
Data Index: 4270866 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5049. Min Range: -4.5049
Max Act: 4.3174. Min Act: -0.1700
Data Index: 4954714 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5049. Min Range: -4.5049
Max Act: 4.3174. Min Act: -0.1700
Data Index: 4785065 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5049. Min Range: -4.5049
Max Act: 4.3174. Min Act: -0.1700
Data Index: 391867 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5049. Min Range: -4.5049
Max Act: 4.3174. Min Act: -0.1700
Data Index: 3010873 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5049. Min Range: -4.5049
Max Act: 4.2862. Min Act: -0.1697
Data Index: 8426189 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5049. Min Range: -4.5049
Max Act: 4.2862. Min Act: -0.1700
Data Index: 3903063 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5049. Min Range: -4.5049
Max Act: 4.2862. Min Act: -0.1700
Data Index: 2369197 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5049. Min Range: -4.5049
Max Act: 4.2549. Min Act: -0.1700
Data Index: 6602135 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5049. Min Range: -4.5049
Max Act: 4.2549. Min Act: -0.1700
Data Index: 4785062 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5049. Min Range: -4.5049
Max Act: 4.2862. Min Act: -0.1700
Data Index: 6096301 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5049. Min Range: -4.5049
Max Act: 4.2549. Min Act: -0.1700
Data Index: 4701475 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5049. Min Range: -4.5049
Max Act: 4.2236. Min Act: -0.1700
Data Index: 4589522 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5049. Min Range: -4.5049
Max Act: 4.2549. Min Act: -0.1700
Data Index: 3499701 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5049. Min Range: -4.5049
Max Act: 4.2549. Min Act: -0.1700
Data Index: 2200974 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5049. Min Range: -4.5049
Max Act: 4.2549. Min Act: -0.1700
Data Index: 2099381 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5049. Min Range: -4.5049
Max Act: 4.2236. Min Act: -0.1700
Data Index: 744617 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5049. Min Range: -4.5049
Max Act: 4.2549. Min Act: -0.1700
Data Index: 522577 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5049. Min Range: -4.5049
Max Act: 4.2549. Min Act: -0.1700
Data Index: 5469627 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19