Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 138 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.9130. Min Act: -0.1700
Data Index: 6742938 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.8817. Min Act: -0.1700
Data Index: 8268446 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.8505. Min Act: -0.1700
Data Index: 795007 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.8192. Min Act: -0.1700
Data Index: 5520198 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.7567. Min Act: -0.1700
Data Index: 273298 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.7880. Min Act: -0.1700
Data Index: 4610086 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.7880. Min Act: -0.1700
Data Index: 7557204 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.7880. Min Act: -0.1700
Data Index: 8826695 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.7880. Min Act: -0.1700
Data Index: 6272003 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.7567. Min Act: -0.1700
Data Index: 8827341 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.7880. Min Act: -0.1700
Data Index: 4726335 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.7567. Min Act: -0.1700
Data Index: 3574481 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.7567. Min Act: -0.1700
Data Index: 3574482 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.7255. Min Act: -0.1700
Data Index: 6869222 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.7255. Min Act: -0.1700
Data Index: 3068659 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.7255. Min Act: -0.1700
Data Index: 5789650 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.7255. Min Act: -0.1700
Data Index: 7704589 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.7255. Min Act: -0.1700
Data Index: 432608 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.7255. Min Act: -0.1700
Data Index: 7384715 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.7255. Min Act: -0.1700
Data Index: 6907898 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19