Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3389 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3377. Min Range: -8.3377
Max Act: 8.3377. Min Act: -0.1700
Data Index: 4030821 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3377. Min Range: -8.3377
Max Act: 8.0252. Min Act: -0.1700
Data Index: 2516415 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3377. Min Range: -8.3377
Max Act: 8.0252. Min Act: -0.1700
Data Index: 3263599 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3377. Min Range: -8.3377
Max Act: 7.8377. Min Act: -0.1700
Data Index: 5409609 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3377. Min Range: -8.3377
Max Act: 7.8377. Min Act: -0.1700
Data Index: 963094 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3377. Min Range: -8.3377
Max Act: 7.7752. Min Act: -0.1700
Data Index: 6271494 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3377. Min Range: -8.3377
Max Act: 7.7127. Min Act: -0.1700
Data Index: 7531352 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3377. Min Range: -8.3377
Max Act: 7.7127. Min Act: -0.1700
Data Index: 2506447 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3377. Min Range: -8.3377
Max Act: 7.6502. Min Act: -0.1700
Data Index: 501424 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3377. Min Range: -8.3377
Max Act: 7.6502. Min Act: -0.1700
Data Index: 7295692 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3377. Min Range: -8.3377
Max Act: 7.6502. Min Act: -0.1700
Data Index: 26520 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3377. Min Range: -8.3377
Max Act: 7.6502. Min Act: -0.1700
Data Index: 7482479 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3377. Min Range: -8.3377
Max Act: 7.5877. Min Act: -0.1700
Data Index: 6815728 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3377. Min Range: -8.3377
Max Act: 7.5877. Min Act: -0.1700
Data Index: 342023 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3377. Min Range: -8.3377
Max Act: 7.5877. Min Act: -0.1700
Data Index: 6806220 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3377. Min Range: -8.3377
Max Act: 7.5877. Min Act: -0.1700
Data Index: 6899859 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3377. Min Range: -8.3377
Max Act: 7.5877. Min Act: -0.1700
Data Index: 4670304 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3377. Min Range: -8.3377
Max Act: 7.5877. Min Act: -0.1700
Data Index: 8736953 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3377. Min Range: -8.3377
Max Act: 7.5877. Min Act: -0.1700
Data Index: 6168490 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3377. Min Range: -8.3377
Max Act: 7.5252. Min Act: -0.1700
Data Index: 2635007 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19