Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2666 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9884. Min Range: -4.9884
Max Act: 4.9572. Min Act: -0.1700
Data Index: 6185141 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9884. Min Range: -4.9884
Max Act: 4.9884. Min Act: -0.1700
Data Index: 7181982 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9884. Min Range: -4.9884
Max Act: 4.9259. Min Act: -0.1700
Data Index: 2257370 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9884. Min Range: -4.9884
Max Act: 4.8947. Min Act: -0.1700
Data Index: 3429481 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9884. Min Range: -4.9884
Max Act: 4.8947. Min Act: -0.1700
Data Index: 7504642 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9884. Min Range: -4.9884
Max Act: 4.8947. Min Act: -0.1700
Data Index: 7438734 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9884. Min Range: -4.9884
Max Act: 4.8634. Min Act: -0.1700
Data Index: 8188416 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9884. Min Range: -4.9884
Max Act: 4.8947. Min Act: -0.1700
Data Index: 7162767 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9884. Min Range: -4.9884
Max Act: 4.8322. Min Act: -0.1700
Data Index: 2424163 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9884. Min Range: -4.9884
Max Act: 4.8322. Min Act: -0.1700
Data Index: 4000569 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9884. Min Range: -4.9884
Max Act: 4.8009. Min Act: -0.1700
Data Index: 5759644 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9884. Min Range: -4.9884
Max Act: 4.8322. Min Act: -0.1700
Data Index: 433028 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9884. Min Range: -4.9884
Max Act: 4.8322. Min Act: -0.1700
Data Index: 6646339 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9884. Min Range: -4.9884
Max Act: 4.7697. Min Act: -0.1700
Data Index: 4185637 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9884. Min Range: -4.9884
Max Act: 4.8009. Min Act: -0.1700
Data Index: 1219110 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9884. Min Range: -4.9884
Max Act: 4.8009. Min Act: -0.1700
Data Index: 3051403 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9884. Min Range: -4.9884
Max Act: 4.8009. Min Act: -0.1700
Data Index: 3105116 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9884. Min Range: -4.9884
Max Act: 4.8009. Min Act: -0.1700
Data Index: 7135208 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9884. Min Range: -4.9884
Max Act: 4.8009. Min Act: -0.1700
Data Index: 6958864 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9884. Min Range: -4.9884
Max Act: 4.8009. Min Act: -0.1700
Data Index: 6155688 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19