Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2934 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7421. Min Range: -6.7421
Max Act: 6.7421. Min Act: -0.1700
Data Index: 5105017 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7421. Min Range: -6.7421
Max Act: 6.7108. Min Act: -0.1700
Data Index: 1321292 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7421. Min Range: -6.7421
Max Act: 6.6483. Min Act: -0.1700
Data Index: 8727442 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7421. Min Range: -6.7421
Max Act: 6.5858. Min Act: -0.1700
Data Index: 7972805 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7421. Min Range: -6.7421
Max Act: 6.5858. Min Act: -0.1700
Data Index: 6673597 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7421. Min Range: -6.7421
Max Act: 6.5546. Min Act: -0.1700
Data Index: 4645402 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7421. Min Range: -6.7421
Max Act: 6.5233. Min Act: -0.1700
Data Index: 46 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7421. Min Range: -6.7421
Max Act: 6.5233. Min Act: -0.1700
Data Index: 5581112 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7421. Min Range: -6.7421
Max Act: 6.4921. Min Act: -0.1700
Data Index: 4344497 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7421. Min Range: -6.7421
Max Act: 6.4921. Min Act: -0.1700
Data Index: 1004091 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7421. Min Range: -6.7421
Max Act: 6.4296. Min Act: -0.1700
Data Index: 4900605 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7421. Min Range: -6.7421
Max Act: 6.4608. Min Act: -0.1700
Data Index: 1470436 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7421. Min Range: -6.7421
Max Act: 6.4608. Min Act: -0.1700
Data Index: 666573 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7421. Min Range: -6.7421
Max Act: 6.3983. Min Act: -0.1700
Data Index: 4514825 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7421. Min Range: -6.7421
Max Act: 6.3983. Min Act: -0.1700
Data Index: 1168389 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7421. Min Range: -6.7421
Max Act: 6.3983. Min Act: -0.1700
Data Index: 4137262 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7421. Min Range: -6.7421
Max Act: 6.3983. Min Act: -0.1700
Data Index: 5672938 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7421. Min Range: -6.7421
Max Act: 6.3671. Min Act: -0.1700
Data Index: 3085081 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7421. Min Range: -6.7421
Max Act: 6.3358. Min Act: -0.1700
Data Index: 723220 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7421. Min Range: -6.7421
Max Act: 6.3358. Min Act: -0.1700
Data Index: 8536022 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19