Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2264 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0277. Min Range: -8.0277
Max Act: 8.0277. Min Act: -0.1700
Data Index: 6951437 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0277. Min Range: -8.0277
Max Act: 7.9652. Min Act: -0.1700
Data Index: 656405 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0277. Min Range: -8.0277
Max Act: 7.9652. Min Act: -0.1700
Data Index: 6833900 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0277. Min Range: -8.0277
Max Act: 7.8402. Min Act: -0.1700
Data Index: 4350141 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0277. Min Range: -8.0277
Max Act: 7.7152. Min Act: -0.1700
Data Index: 5264965 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0277. Min Range: -8.0277
Max Act: 7.7465. Min Act: -0.1700
Data Index: 2927515 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0277. Min Range: -8.0277
Max Act: 7.6840. Min Act: -0.1700
Data Index: 5385730 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0277. Min Range: -8.0277
Max Act: 7.6840. Min Act: -0.1700
Data Index: 5082311 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0277. Min Range: -8.0277
Max Act: 7.6527. Min Act: -0.1700
Data Index: 8748733 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0277. Min Range: -8.0277
Max Act: 7.6215. Min Act: -0.1700
Data Index: 2902463 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0277. Min Range: -8.0277
Max Act: 7.5902. Min Act: -0.1700
Data Index: 6845018 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0277. Min Range: -8.0277
Max Act: 7.6215. Min Act: -0.1700
Data Index: 1108048 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0277. Min Range: -8.0277
Max Act: 7.5277. Min Act: -0.1700
Data Index: 5039342 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0277. Min Range: -8.0277
Max Act: 7.5590. Min Act: -0.1700
Data Index: 7484144 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0277. Min Range: -8.0277
Max Act: 7.5277. Min Act: -0.1700
Data Index: 803911 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0277. Min Range: -8.0277
Max Act: 7.4965. Min Act: -0.1700
Data Index: 1521255 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0277. Min Range: -8.0277
Max Act: 7.4965. Min Act: -0.1700
Data Index: 7469435 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0277. Min Range: -8.0277
Max Act: 7.4652. Min Act: -0.1700
Data Index: 7661723 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0277. Min Range: -8.0277
Max Act: 7.4652. Min Act: -0.1700
Data Index: 4873864 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0277. Min Range: -8.0277
Max Act: 7.4652. Min Act: -0.1700
Data Index: 4821292 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19