Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1373 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8983. Min Range: -6.8983
Max Act: 6.8983. Min Act: -0.1700
Data Index: 5788364 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8983. Min Range: -6.8983
Max Act: 6.7733. Min Act: -0.1700
Data Index: 4920436 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8983. Min Range: -6.8983
Max Act: 6.6170. Min Act: -0.1700
Data Index: 4389990 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8983. Min Range: -6.8983
Max Act: 6.5858. Min Act: -0.1700
Data Index: 8042297 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8983. Min Range: -6.8983
Max Act: 6.5858. Min Act: -0.1700
Data Index: 7608717 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8983. Min Range: -6.8983
Max Act: 6.5858. Min Act: -0.1700
Data Index: 3034493 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8983. Min Range: -6.8983
Max Act: 6.5545. Min Act: -0.1700
Data Index: 6115254 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8983. Min Range: -6.8983
Max Act: 6.5233. Min Act: -0.1700
Data Index: 21724 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8983. Min Range: -6.8983
Max Act: 6.5233. Min Act: -0.1700
Data Index: 8230258 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8983. Min Range: -6.8983
Max Act: 6.5233. Min Act: -0.1700
Data Index: 6420464 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8983. Min Range: -6.8983
Max Act: 6.4920. Min Act: -0.1700
Data Index: 5442610 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8983. Min Range: -6.8983
Max Act: 6.5233. Min Act: -0.1700
Data Index: 3693497 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8983. Min Range: -6.8983
Max Act: 6.5233. Min Act: -0.1700
Data Index: 7362678 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8983. Min Range: -6.8983
Max Act: 6.4920. Min Act: -0.1700
Data Index: 2219624 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8983. Min Range: -6.8983
Max Act: 6.4920. Min Act: -0.1700
Data Index: 8088310 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8983. Min Range: -6.8983
Max Act: 6.4920. Min Act: -0.1700
Data Index: 8145187 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8983. Min Range: -6.8983
Max Act: 6.4608. Min Act: -0.1700
Data Index: 3738119 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8983. Min Range: -6.8983
Max Act: 6.4608. Min Act: -0.1700
Data Index: 4029210 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8983. Min Range: -6.8983
Max Act: 6.4608. Min Act: -0.1700
Data Index: 4903196 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8983. Min Range: -6.8983
Max Act: 6.4295. Min Act: -0.1700
Data Index: 6245108 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19