Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1413 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3147. Min Range: -6.3147
Max Act: 6.3147. Min Act: -0.1700
Data Index: 7764190 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3147. Min Range: -6.3147
Max Act: 6.2210. Min Act: -0.1700
Data Index: 7194589 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3147. Min Range: -6.3147
Max Act: 6.0335. Min Act: -0.1700
Data Index: 751638 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3147. Min Range: -6.3147
Max Act: 5.9085. Min Act: -0.1700
Data Index: 3368612 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3147. Min Range: -6.3147
Max Act: 5.8772. Min Act: -0.1700
Data Index: 3428386 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3147. Min Range: -6.3147
Max Act: 5.8460. Min Act: -0.1700
Data Index: 2543458 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3147. Min Range: -6.3147
Max Act: 5.8147. Min Act: -0.1700
Data Index: 4491284 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3147. Min Range: -6.3147
Max Act: 5.8147. Min Act: -0.1700
Data Index: 286239 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3147. Min Range: -6.3147
Max Act: 5.6897. Min Act: -0.1700
Data Index: 608357 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3147. Min Range: -6.3147
Max Act: 5.7210. Min Act: -0.1700
Data Index: 4513035 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3147. Min Range: -6.3147
Max Act: 5.6897. Min Act: -0.1700
Data Index: 6356761 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3147. Min Range: -6.3147
Max Act: 5.6897. Min Act: -0.1700
Data Index: 3360636 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3147. Min Range: -6.3147
Max Act: 5.6585. Min Act: -0.1700
Data Index: 4226480 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3147. Min Range: -6.3147
Max Act: 5.6585. Min Act: -0.1700
Data Index: 635391 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3147. Min Range: -6.3147
Max Act: 5.6272. Min Act: -0.1700
Data Index: 3517484 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3147. Min Range: -6.3147
Max Act: 5.6272. Min Act: -0.1700
Data Index: 2957455 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3147. Min Range: -6.3147
Max Act: 5.6272. Min Act: -0.1700
Data Index: 5558836 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3147. Min Range: -6.3147
Max Act: 5.5647. Min Act: -0.1700
Data Index: 7848001 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3147. Min Range: -6.3147
Max Act: 5.5647. Min Act: -0.1700
Data Index: 8820461 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3147. Min Range: -6.3147
Max Act: 5.5647. Min Act: -0.1700
Data Index: 1677618 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19