Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3464 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9105. Min Range: -4.9105
Max Act: 4.9105. Min Act: -0.1700
Data Index: 8733761 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9105. Min Range: -4.9105
Max Act: 4.8793. Min Act: -0.1700
Data Index: 1543585 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9105. Min Range: -4.9105
Max Act: 4.7230. Min Act: -0.1700
Data Index: 6386144 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9105. Min Range: -4.9105
Max Act: 4.5980. Min Act: -0.1700
Data Index: 8328873 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9105. Min Range: -4.9105
Max Act: 4.5668. Min Act: -0.1700
Data Index: 4200986 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9105. Min Range: -4.9105
Max Act: 4.5355. Min Act: -0.1700
Data Index: 7712023 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9105. Min Range: -4.9105
Max Act: 4.5355. Min Act: -0.1700
Data Index: 1877725 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9105. Min Range: -4.9105
Max Act: 4.5355. Min Act: -0.1700
Data Index: 33105 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9105. Min Range: -4.9105
Max Act: 4.5042. Min Act: -0.1700
Data Index: 573695 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9105. Min Range: -4.9105
Max Act: 4.5042. Min Act: -0.1700
Data Index: 5991038 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9105. Min Range: -4.9105
Max Act: 4.4730. Min Act: -0.1700
Data Index: 2005766 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9105. Min Range: -4.9105
Max Act: 4.4730. Min Act: -0.1700
Data Index: 1199466 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9105. Min Range: -4.9105
Max Act: 4.4730. Min Act: -0.1700
Data Index: 2599299 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9105. Min Range: -4.9105
Max Act: 4.4417. Min Act: -0.1700
Data Index: 1068702 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9105. Min Range: -4.9105
Max Act: 4.4730. Min Act: -0.1700
Data Index: 2536716 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9105. Min Range: -4.9105
Max Act: 4.4417. Min Act: -0.1700
Data Index: 4972190 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9105. Min Range: -4.9105
Max Act: 4.4105. Min Act: -0.1700
Data Index: 4922535 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9105. Min Range: -4.9105
Max Act: 4.4105. Min Act: -0.1700
Data Index: 3204868 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9105. Min Range: -4.9105
Max Act: 4.4105. Min Act: -0.1700
Data Index: 3817127 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9105. Min Range: -4.9105
Max Act: 4.4105. Min Act: -0.1700
Data Index: 6651627 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19