Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1176 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1130. Min Range: -5.1130
Max Act: 5.1130. Min Act: -0.1700
Data Index: 241800 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1130. Min Range: -5.1130
Max Act: 5.0817. Min Act: -0.1700
Data Index: 4280775 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1130. Min Range: -5.1130
Max Act: 5.0192. Min Act: -0.1700
Data Index: 929283 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1130. Min Range: -5.1130
Max Act: 5.0192. Min Act: -0.1700
Data Index: 603853 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.9880. Min Act: -0.1700
Data Index: 699075 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1130. Min Range: -5.1130
Max Act: 5.0192. Min Act: -0.1700
Data Index: 3464456 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.9567. Min Act: -0.1700
Data Index: 7762508 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.9880. Min Act: -0.1700
Data Index: 1711504 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.9567. Min Act: -0.1700
Data Index: 6992188 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.9567. Min Act: -0.1700
Data Index: 2230349 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.9255. Min Act: -0.1700
Data Index: 4324909 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.9255. Min Act: -0.1700
Data Index: 4535927 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.9255. Min Act: -0.1700
Data Index: 5921633 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.9255. Min Act: -0.1700
Data Index: 3192281 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.9567. Min Act: -0.1700
Data Index: 6404142 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.9255. Min Act: -0.1700
Data Index: 8772093 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.9255. Min Act: -0.1700
Data Index: 4249119 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.8942. Min Act: -0.1700
Data Index: 361425 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.8942. Min Act: -0.1700
Data Index: 4544896 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.8630. Min Act: -0.1700
Data Index: 253296 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19