Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 56 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.6345. Min Act: -0.1700
Data Index: 5114575 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.6657. Min Act: -0.1700
Data Index: 2889335 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.6657. Min Act: -0.1700
Data Index: 5261851 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.6345. Min Act: -0.1700
Data Index: 8086976 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.6345. Min Act: -0.1700
Data Index: 7030534 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.5720. Min Act: -0.1700
Data Index: 789554 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.5407. Min Act: -0.1700
Data Index: 5929084 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.5720. Min Act: -0.1700
Data Index: 4685341 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.5407. Min Act: -0.1700
Data Index: 4367059 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.5720. Min Act: -0.1700
Data Index: 6929030 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.5407. Min Act: -0.1700
Data Index: 8540516 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.5407. Min Act: -0.1700
Data Index: 2996818 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.5095. Min Act: -0.1700
Data Index: 7010784 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.5095. Min Act: -0.1700
Data Index: 3402253 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.5095. Min Act: -0.1700
Data Index: 8135950 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.5095. Min Act: -0.1700
Data Index: 3486891 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.5407. Min Act: -0.1700
Data Index: 6980536 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.4782. Min Act: -0.1700
Data Index: 7607725 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.4782. Min Act: -0.1700
Data Index: 7438129 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6657. Min Range: -6.6657
Max Act: 6.4782. Min Act: -0.1700
Data Index: 2658945 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19