Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3350 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0245. Min Range: -7.0245
Max Act: 7.0245. Min Act: -0.1700
Data Index: 355115 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0245. Min Range: -7.0245
Max Act: 6.9308. Min Act: -0.1700
Data Index: 666653 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0245. Min Range: -7.0245
Max Act: 6.7433. Min Act: -0.1700
Data Index: 366144 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0245. Min Range: -7.0245
Max Act: 6.7120. Min Act: -0.1700
Data Index: 2658500 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0245. Min Range: -7.0245
Max Act: 6.6495. Min Act: -0.1700
Data Index: 697502 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0245. Min Range: -7.0245
Max Act: 6.6495. Min Act: -0.1700
Data Index: 1401301 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0245. Min Range: -7.0245
Max Act: 6.6808. Min Act: -0.1700
Data Index: 5749458 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0245. Min Range: -7.0245
Max Act: 6.6495. Min Act: -0.1700
Data Index: 6514990 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0245. Min Range: -7.0245
Max Act: 6.6808. Min Act: -0.1700
Data Index: 1879532 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0245. Min Range: -7.0245
Max Act: 6.6183. Min Act: -0.1700
Data Index: 2960431 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0245. Min Range: -7.0245
Max Act: 6.6495. Min Act: -0.1700
Data Index: 8581758 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0245. Min Range: -7.0245
Max Act: 6.6495. Min Act: -0.1700
Data Index: 3498746 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0245. Min Range: -7.0245
Max Act: 6.6183. Min Act: -0.1700
Data Index: 3056912 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0245. Min Range: -7.0245
Max Act: 6.5870. Min Act: -0.1700
Data Index: 7328918 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0245. Min Range: -7.0245
Max Act: 6.5558. Min Act: -0.1700
Data Index: 247325 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0245. Min Range: -7.0245
Max Act: 6.5870. Min Act: -0.1700
Data Index: 6122893 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0245. Min Range: -7.0245
Max Act: 6.5558. Min Act: -0.1700
Data Index: 5529488 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0245. Min Range: -7.0245
Max Act: 6.5870. Min Act: -0.1700
Data Index: 8652312 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0245. Min Range: -7.0245
Max Act: 6.4933. Min Act: -0.1700
Data Index: 4250429 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0245. Min Range: -7.0245
Max Act: 6.4933. Min Act: -0.1700
Data Index: 3957969 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19