Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 49 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 9.6673. Min Range: -9.6673
Max Act: 9.6673. Min Act: -0.1700
Data Index: 8658907 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6673. Min Range: -9.6673
Max Act: 9.5423. Min Act: -0.1700
Data Index: 8234516 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6673. Min Range: -9.6673
Max Act: 9.5423. Min Act: -0.1700
Data Index: 4045975 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6673. Min Range: -9.6673
Max Act: 9.5423. Min Act: -0.1700
Data Index: 7331498 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6673. Min Range: -9.6673
Max Act: 9.2923. Min Act: -0.1700
Data Index: 6216175 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6673. Min Range: -9.6673
Max Act: 9.4173. Min Act: -0.1700
Data Index: 7776747 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6673. Min Range: -9.6673
Max Act: 9.3548. Min Act: -0.1700
Data Index: 2308254 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6673. Min Range: -9.6673
Max Act: 9.2923. Min Act: -0.1700
Data Index: 3407600 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6673. Min Range: -9.6673
Max Act: 9.3548. Min Act: -0.1700
Data Index: 3458820 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6673. Min Range: -9.6673
Max Act: 9.3548. Min Act: -0.1700
Data Index: 7776763 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6673. Min Range: -9.6673
Max Act: 9.2923. Min Act: -0.1700
Data Index: 8050093 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6673. Min Range: -9.6673
Max Act: 9.2923. Min Act: -0.1700
Data Index: 5806698 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6673. Min Range: -9.6673
Max Act: 9.2923. Min Act: -0.1700
Data Index: 5563731 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6673. Min Range: -9.6673
Max Act: 9.2298. Min Act: -0.1700
Data Index: 1249511 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6673. Min Range: -9.6673
Max Act: 9.2923. Min Act: -0.1700
Data Index: 6485275 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6673. Min Range: -9.6673
Max Act: 9.2298. Min Act: -0.1700
Data Index: 4210708 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6673. Min Range: -9.6673
Max Act: 9.2923. Min Act: -0.1700
Data Index: 4318906 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6673. Min Range: -9.6673
Max Act: 9.1673. Min Act: -0.1700
Data Index: 1770509 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6673. Min Range: -9.6673
Max Act: 9.2298. Min Act: -0.1700
Data Index: 2974325 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6673. Min Range: -9.6673
Max Act: 9.1673. Min Act: -0.1700
Data Index: 1016172 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19