Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 461 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4177. Min Range: -4.4177
Max Act: 4.4177. Min Act: -0.1700
Data Index: 4569033 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4177. Min Range: -4.4177
Max Act: 4.4177. Min Act: -0.1700
Data Index: 6152631 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4177. Min Range: -4.4177
Max Act: 4.3552. Min Act: -0.1700
Data Index: 8030893 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4177. Min Range: -4.4177
Max Act: 4.3240. Min Act: -0.1700
Data Index: 143403 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4177. Min Range: -4.4177
Max Act: 4.2927. Min Act: -0.1700
Data Index: 3875755 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4177. Min Range: -4.4177
Max Act: 4.2615. Min Act: -0.1700
Data Index: 1680991 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4177. Min Range: -4.4177
Max Act: 4.1677. Min Act: -0.1700
Data Index: 6274075 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4177. Min Range: -4.4177
Max Act: 4.1052. Min Act: -0.1700
Data Index: 54944 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4177. Min Range: -4.4177
Max Act: 4.1052. Min Act: -0.1700
Data Index: 4385254 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4177. Min Range: -4.4177
Max Act: 4.0427. Min Act: -0.1700
Data Index: 5725810 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4177. Min Range: -4.4177
Max Act: 4.0427. Min Act: -0.1700
Data Index: 629277 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4177. Min Range: -4.4177
Max Act: 4.0114. Min Act: -0.1700
Data Index: 1901904 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4177. Min Range: -4.4177
Max Act: 4.0427. Min Act: -0.1700
Data Index: 833326 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4177. Min Range: -4.4177
Max Act: 4.0114. Min Act: -0.1700
Data Index: 5922548 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4177. Min Range: -4.4177
Max Act: 3.9802. Min Act: -0.1700
Data Index: 6730317 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4177. Min Range: -4.4177
Max Act: 3.9802. Min Act: -0.1700
Data Index: 6402356 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4177. Min Range: -4.4177
Max Act: 4.0114. Min Act: -0.1700
Data Index: 1521502 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4177. Min Range: -4.4177
Max Act: 3.9489. Min Act: -0.1700
Data Index: 6089793 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4177. Min Range: -4.4177
Max Act: 3.9489. Min Act: -0.1700
Data Index: 2141238 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4177. Min Range: -4.4177
Max Act: 3.9489. Min Act: -0.1700
Data Index: 1896214 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19