Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2190 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.8147. Min Act: -0.1700
Data Index: 1378616 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.6897. Min Act: -0.1700
Data Index: 506597 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.6272. Min Act: -0.1700
Data Index: 2310305 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.5647. Min Act: -0.1700
Data Index: 5735670 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.5022. Min Act: -0.1700
Data Index: 1877267 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.5022. Min Act: -0.1700
Data Index: 8224748 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.4709. Min Act: -0.1700
Data Index: 7040677 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.4397. Min Act: -0.1700
Data Index: 511917 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.4084. Min Act: -0.1700
Data Index: 5274513 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.3772. Min Act: -0.1700
Data Index: 3572143 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.3772. Min Act: -0.1700
Data Index: 2987098 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.3772. Min Act: -0.1700
Data Index: 1454011 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.3772. Min Act: -0.1700
Data Index: 4664898 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.3459. Min Act: -0.1700
Data Index: 6549277 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.3772. Min Act: -0.1700
Data Index: 4099123 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.3772. Min Act: -0.1700
Data Index: 8014341 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.3459. Min Act: -0.1700
Data Index: 541318 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.3459. Min Act: -0.1700
Data Index: 7041870 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.3459. Min Act: -0.1700
Data Index: 384590 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.3772. Min Act: -0.1700
Data Index: 669341 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19