Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3105 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1212. Min Range: -6.1212
Max Act: 6.1212. Min Act: -0.1700
Data Index: 3569229 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1212. Min Range: -6.1212
Max Act: 6.0587. Min Act: -0.1700
Data Index: 2354042 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1212. Min Range: -6.1212
Max Act: 5.9962. Min Act: -0.1700
Data Index: 525520 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1212. Min Range: -6.1212
Max Act: 5.9650. Min Act: -0.1700
Data Index: 3309118 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1212. Min Range: -6.1212
Max Act: 5.9650. Min Act: -0.1700
Data Index: 3197815 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1212. Min Range: -6.1212
Max Act: 5.9337. Min Act: -0.1700
Data Index: 1163386 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1212. Min Range: -6.1212
Max Act: 5.9337. Min Act: -0.1700
Data Index: 7671103 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1212. Min Range: -6.1212
Max Act: 5.9025. Min Act: -0.1700
Data Index: 6617223 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1212. Min Range: -6.1212
Max Act: 5.8712. Min Act: -0.1700
Data Index: 1865142 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1212. Min Range: -6.1212
Max Act: 5.8712. Min Act: -0.1700
Data Index: 5266117 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1212. Min Range: -6.1212
Max Act: 5.8712. Min Act: -0.1700
Data Index: 3764267 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1212. Min Range: -6.1212
Max Act: 5.8087. Min Act: -0.1700
Data Index: 1106267 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1212. Min Range: -6.1212
Max Act: 5.8087. Min Act: -0.1700
Data Index: 7687601 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1212. Min Range: -6.1212
Max Act: 5.8087. Min Act: -0.1700
Data Index: 3066823 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1212. Min Range: -6.1212
Max Act: 5.8087. Min Act: -0.1700
Data Index: 8382063 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1212. Min Range: -6.1212
Max Act: 5.7775. Min Act: -0.1700
Data Index: 464336 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1212. Min Range: -6.1212
Max Act: 5.7150. Min Act: -0.1700
Data Index: 5643904 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1212. Min Range: -6.1212
Max Act: 5.7775. Min Act: -0.1700
Data Index: 7131100 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1212. Min Range: -6.1212
Max Act: 5.7462. Min Act: -0.1700
Data Index: 4260502 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1212. Min Range: -6.1212
Max Act: 5.7462. Min Act: -0.1700
Data Index: 525521 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19