Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2862 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8244. Min Range: -7.8244
Max Act: 7.8244. Min Act: -0.1700
Data Index: 3284566 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8244. Min Range: -7.8244
Max Act: 7.6681. Min Act: -0.1700
Data Index: 8266394 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8244. Min Range: -7.8244
Max Act: 7.4181. Min Act: -0.1700
Data Index: 2001412 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8244. Min Range: -7.8244
Max Act: 7.3869. Min Act: -0.1700
Data Index: 1225638 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8244. Min Range: -7.8244
Max Act: 7.3869. Min Act: -0.1700
Data Index: 861141 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8244. Min Range: -7.8244
Max Act: 7.3869. Min Act: -0.1700
Data Index: 8631845 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8244. Min Range: -7.8244
Max Act: 7.3556. Min Act: -0.1700
Data Index: 7156938 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8244. Min Range: -7.8244
Max Act: 7.1994. Min Act: -0.1700
Data Index: 1786689 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8244. Min Range: -7.8244
Max Act: 7.2306. Min Act: -0.1700
Data Index: 5483761 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8244. Min Range: -7.8244
Max Act: 7.2306. Min Act: -0.1700
Data Index: 1225641 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8244. Min Range: -7.8244
Max Act: 7.2619. Min Act: -0.1700
Data Index: 1805576 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8244. Min Range: -7.8244
Max Act: 7.2306. Min Act: -0.1700
Data Index: 5300998 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8244. Min Range: -7.8244
Max Act: 7.1994. Min Act: -0.1700
Data Index: 6441950 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8244. Min Range: -7.8244
Max Act: 7.1994. Min Act: -0.1700
Data Index: 5410204 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8244. Min Range: -7.8244
Max Act: 7.1994. Min Act: -0.1700
Data Index: 3433800 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8244. Min Range: -7.8244
Max Act: 7.1056. Min Act: -0.1700
Data Index: 3799120 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8244. Min Range: -7.8244
Max Act: 7.1056. Min Act: -0.1700
Data Index: 4462157 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8244. Min Range: -7.8244
Max Act: 7.0744. Min Act: -0.1700
Data Index: 7690294 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8244. Min Range: -7.8244
Max Act: 7.0744. Min Act: -0.1700
Data Index: 8807056 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8244. Min Range: -7.8244
Max Act: 7.0431. Min Act: -0.1700
Data Index: 5133365 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19