Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1554. Min Range: -9.1554
Max Act: 9.1554. Min Act: -0.1700
Data Index: 3386822 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1554. Min Range: -9.1554
Max Act: 9.1554. Min Act: -0.1700
Data Index: 3177636 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1554. Min Range: -9.1554
Max Act: 9.1554. Min Act: -0.1700
Data Index: 1662681 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1554. Min Range: -9.1554
Max Act: 9.0929. Min Act: -0.1700
Data Index: 6966284 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1554. Min Range: -9.1554
Max Act: 9.0304. Min Act: -0.1700
Data Index: 2300671 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1554. Min Range: -9.1554
Max Act: 8.9054. Min Act: -0.1700
Data Index: 1871767 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1554. Min Range: -9.1554
Max Act: 8.7804. Min Act: -0.1700
Data Index: 8291062 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1554. Min Range: -9.1554
Max Act: 8.7179. Min Act: -0.1700
Data Index: 1237395 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1554. Min Range: -9.1554
Max Act: 8.6554. Min Act: -0.1700
Data Index: 3914521 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1554. Min Range: -9.1554
Max Act: 8.6554. Min Act: -0.1700
Data Index: 8782863 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1554. Min Range: -9.1554
Max Act: 8.6554. Min Act: -0.1700
Data Index: 801910 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1554. Min Range: -9.1554
Max Act: 8.6554. Min Act: -0.1700
Data Index: 2925192 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1554. Min Range: -9.1554
Max Act: 8.6554. Min Act: -0.1700
Data Index: 29721 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1554. Min Range: -9.1554
Max Act: 8.5929. Min Act: -0.1700
Data Index: 4094271 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1554. Min Range: -9.1554
Max Act: 8.5929. Min Act: -0.1700
Data Index: 7616366 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1554. Min Range: -9.1554
Max Act: 8.5929. Min Act: -0.1700
Data Index: 3577914 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1554. Min Range: -9.1554
Max Act: 8.5929. Min Act: -0.1700
Data Index: 7811713 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1554. Min Range: -9.1554
Max Act: 8.4679. Min Act: -0.1700
Data Index: 6953642 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1554. Min Range: -9.1554
Max Act: 8.5304. Min Act: -0.1700
Data Index: 6783703 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1554. Min Range: -9.1554
Max Act: 8.5304. Min Act: -0.1700
Data Index: 2628942 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19