Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 661 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0341. Min Range: -6.0341
Max Act: 6.0341. Min Act: -0.1700
Data Index: 1087328 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.9403. Min Act: -0.1700
Data Index: 7927723 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.9091. Min Act: -0.1700
Data Index: 6188148 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.7216. Min Act: -0.1700
Data Index: 5728869 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.6903. Min Act: -0.1700
Data Index: 3373038 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.6903. Min Act: -0.1700
Data Index: 8772917 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.6591. Min Act: -0.1700
Data Index: 4574371 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.6591. Min Act: -0.1700
Data Index: 6753122 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.6278. Min Act: -0.1700
Data Index: 5554317 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.6591. Min Act: -0.1700
Data Index: 7192557 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.6278. Min Act: -0.1700
Data Index: 8757320 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.6278. Min Act: -0.1700
Data Index: 4659503 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.5966. Min Act: -0.1700
Data Index: 4467033 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.6278. Min Act: -0.1700
Data Index: 7857221 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.5966. Min Act: -0.1700
Data Index: 4858915 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.5966. Min Act: -0.1700
Data Index: 4597718 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.5966. Min Act: -0.1700
Data Index: 2559205 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.5966. Min Act: -0.1700
Data Index: 3793308 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.5966. Min Act: -0.1700
Data Index: 1699857 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.5653. Min Act: -0.1700
Data Index: 2120948 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19