Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1657. Min Range: -5.1657
Max Act: 5.1657. Min Act: -0.1700
Data Index: 1285150 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1657. Min Range: -5.1657
Max Act: 5.1345. Min Act: -0.1700
Data Index: 836892 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1657. Min Range: -5.1657
Max Act: 5.1345. Min Act: -0.1700
Data Index: 635041 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1657. Min Range: -5.1657
Max Act: 5.0720. Min Act: -0.1700
Data Index: 4086731 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1657. Min Range: -5.1657
Max Act: 5.0720. Min Act: -0.1700
Data Index: 3936853 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1657. Min Range: -5.1657
Max Act: 5.0720. Min Act: -0.1700
Data Index: 5659212 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1657. Min Range: -5.1657
Max Act: 5.0720. Min Act: -0.1700
Data Index: 8257889 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1657. Min Range: -5.1657
Max Act: 5.0407. Min Act: -0.1700
Data Index: 8319109 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1657. Min Range: -5.1657
Max Act: 5.0407. Min Act: -0.1700
Data Index: 2730096 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1657. Min Range: -5.1657
Max Act: 5.0720. Min Act: -0.1700
Data Index: 8794177 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1657. Min Range: -5.1657
Max Act: 5.0407. Min Act: -0.1700
Data Index: 4086732 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1657. Min Range: -5.1657
Max Act: 5.0407. Min Act: -0.1700
Data Index: 252273 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1657. Min Range: -5.1657
Max Act: 5.0407. Min Act: -0.1700
Data Index: 6560798 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1657. Min Range: -5.1657
Max Act: 5.0095. Min Act: -0.1700
Data Index: 8633210 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1657. Min Range: -5.1657
Max Act: 5.0095. Min Act: -0.1700
Data Index: 6942012 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1657. Min Range: -5.1657
Max Act: 4.9782. Min Act: -0.1700
Data Index: 5311882 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1657. Min Range: -5.1657
Max Act: 4.9782. Min Act: -0.1700
Data Index: 4382723 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1657. Min Range: -5.1657
Max Act: 4.9782. Min Act: -0.1700
Data Index: 6848371 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1657. Min Range: -5.1657
Max Act: 4.9782. Min Act: -0.1700
Data Index: 5771836 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1657. Min Range: -5.1657
Max Act: 4.9470. Min Act: -0.1700
Data Index: 525232 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19