Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3101 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9613. Min Range: -6.9613
Max Act: 6.9613. Min Act: -0.1700
Data Index: 8158364 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9613. Min Range: -6.9613
Max Act: 6.9613. Min Act: -0.1700
Data Index: 5364035 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9613. Min Range: -6.9613
Max Act: 6.8675. Min Act: -0.1700
Data Index: 2765097 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9613. Min Range: -6.9613
Max Act: 6.7738. Min Act: -0.1700
Data Index: 6767641 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9613. Min Range: -6.9613
Max Act: 6.7738. Min Act: -0.1700
Data Index: 1767875 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9613. Min Range: -6.9613
Max Act: 6.7425. Min Act: -0.1700
Data Index: 6440975 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9613. Min Range: -6.9613
Max Act: 6.7425. Min Act: -0.1700
Data Index: 3591269 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9613. Min Range: -6.9613
Max Act: 6.7113. Min Act: -0.1700
Data Index: 3658816 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9613. Min Range: -6.9613
Max Act: 6.7113. Min Act: -0.1700
Data Index: 4583465 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9613. Min Range: -6.9613
Max Act: 6.7113. Min Act: -0.1700
Data Index: 197117 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9613. Min Range: -6.9613
Max Act: 6.7425. Min Act: -0.1700
Data Index: 2349143 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9613. Min Range: -6.9613
Max Act: 6.7113. Min Act: -0.1700
Data Index: 8558847 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9613. Min Range: -6.9613
Max Act: 6.6800. Min Act: -0.1700
Data Index: 4904547 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9613. Min Range: -6.9613
Max Act: 6.6800. Min Act: -0.1700
Data Index: 5696249 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9613. Min Range: -6.9613
Max Act: 6.6488. Min Act: -0.1700
Data Index: 1804903 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9613. Min Range: -6.9613
Max Act: 6.6488. Min Act: -0.1700
Data Index: 1223962 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9613. Min Range: -6.9613
Max Act: 6.6488. Min Act: -0.1700
Data Index: 4547947 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9613. Min Range: -6.9613
Max Act: 6.6175. Min Act: -0.1700
Data Index: 5820596 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9613. Min Range: -6.9613
Max Act: 6.6175. Min Act: -0.1700
Data Index: 4201594 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9613. Min Range: -6.9613
Max Act: 6.6175. Min Act: -0.1700
Data Index: 7652743 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19