Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3521 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7585. Min Range: -8.7585
Max Act: 8.7585. Min Act: -0.1700
Data Index: 3507375 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7585. Min Range: -8.7585
Max Act: 8.1960. Min Act: -0.1700
Data Index: 7815579 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7585. Min Range: -8.7585
Max Act: 7.9460. Min Act: -0.1700
Data Index: 4835791 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7585. Min Range: -8.7585
Max Act: 7.8835. Min Act: -0.1700
Data Index: 721632 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7585. Min Range: -8.7585
Max Act: 7.8210. Min Act: -0.1700
Data Index: 3770430 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7585. Min Range: -8.7585
Max Act: 7.7585. Min Act: -0.1700
Data Index: 2563836 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7585. Min Range: -8.7585
Max Act: 7.7585. Min Act: -0.1700
Data Index: 568589 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7585. Min Range: -8.7585
Max Act: 7.6960. Min Act: -0.1700
Data Index: 1433600 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7585. Min Range: -8.7585
Max Act: 7.6335. Min Act: -0.1700
Data Index: 8517894 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7585. Min Range: -8.7585
Max Act: 7.6335. Min Act: -0.1700
Data Index: 1776137 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7585. Min Range: -8.7585
Max Act: 7.5397. Min Act: -0.1700
Data Index: 6255976 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7585. Min Range: -8.7585
Max Act: 7.5085. Min Act: -0.1700
Data Index: 916515 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7585. Min Range: -8.7585
Max Act: 7.5085. Min Act: -0.1700
Data Index: 8371562 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7585. Min Range: -8.7585
Max Act: 7.5085. Min Act: -0.1700
Data Index: 1219011 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7585. Min Range: -8.7585
Max Act: 7.4772. Min Act: -0.1700
Data Index: 7157308 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7585. Min Range: -8.7585
Max Act: 7.4460. Min Act: -0.1700
Data Index: 3780448 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7585. Min Range: -8.7585
Max Act: 7.5085. Min Act: -0.1700
Data Index: 2586152 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7585. Min Range: -8.7585
Max Act: 7.4147. Min Act: -0.1700
Data Index: 4118992 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7585. Min Range: -8.7585
Max Act: 7.3210. Min Act: -0.1700
Data Index: 3840156 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7585. Min Range: -8.7585
Max Act: 7.3835. Min Act: -0.1700
Data Index: 1948935 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19