Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3327 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3530. Min Range: -7.3530
Max Act: 7.3530. Min Act: -0.1700
Data Index: 877713 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3530. Min Range: -7.3530
Max Act: 7.2280. Min Act: -0.1700
Data Index: 795561 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3530. Min Range: -7.3530
Max Act: 6.8842. Min Act: -0.1700
Data Index: 421423 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3530. Min Range: -7.3530
Max Act: 6.8842. Min Act: -0.1700
Data Index: 1405217 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3530. Min Range: -7.3530
Max Act: 6.8530. Min Act: -0.1700
Data Index: 6614779 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3530. Min Range: -7.3530
Max Act: 6.7592. Min Act: -0.1700
Data Index: 5380790 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3530. Min Range: -7.3530
Max Act: 6.7280. Min Act: -0.1700
Data Index: 1216373 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3530. Min Range: -7.3530
Max Act: 6.7280. Min Act: -0.1700
Data Index: 532861 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3530. Min Range: -7.3530
Max Act: 6.6967. Min Act: -0.1700
Data Index: 7571167 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3530. Min Range: -7.3530
Max Act: 6.6342. Min Act: -0.1700
Data Index: 4457607 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3530. Min Range: -7.3530
Max Act: 6.6342. Min Act: -0.1700
Data Index: 7814273 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3530. Min Range: -7.3530
Max Act: 6.6030. Min Act: -0.1700
Data Index: 8297350 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3530. Min Range: -7.3530
Max Act: 6.6030. Min Act: -0.1700
Data Index: 4222254 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3530. Min Range: -7.3530
Max Act: 6.5717. Min Act: -0.1700
Data Index: 8754654 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3530. Min Range: -7.3530
Max Act: 6.5405. Min Act: -0.1700
Data Index: 3365168 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3530. Min Range: -7.3530
Max Act: 6.5405. Min Act: -0.1700
Data Index: 5070581 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3530. Min Range: -7.3530
Max Act: 6.5405. Min Act: -0.1700
Data Index: 3843477 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3530. Min Range: -7.3530
Max Act: 6.5092. Min Act: -0.1700
Data Index: 2647619 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3530. Min Range: -7.3530
Max Act: 6.5092. Min Act: -0.1700
Data Index: 6411011 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3530. Min Range: -7.3530
Max Act: 6.5092. Min Act: -0.1700
Data Index: 4815151 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19