Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1875 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7807. Min Range: -2.7807
Max Act: 2.7807. Min Act: -0.1700
Data Index: 6204148 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7807. Min Range: -2.7807
Max Act: 2.7807. Min Act: -0.1700
Data Index: 5560247 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7807. Min Range: -2.7807
Max Act: 2.6849. Min Act: -0.1700
Data Index: 1585639 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7807. Min Range: -2.7807
Max Act: 2.7169. Min Act: -0.1700
Data Index: 4989141 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7807. Min Range: -2.7807
Max Act: 2.6528. Min Act: -0.1700
Data Index: 6858172 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7807. Min Range: -2.7807
Max Act: 2.6689. Min Act: -0.1700
Data Index: 2221768 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7807. Min Range: -2.7807
Max Act: 2.6368. Min Act: -0.1700
Data Index: 2618779 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7807. Min Range: -2.7807
Max Act: 2.6368. Min Act: -0.1700
Data Index: 1844133 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7807. Min Range: -2.7807
Max Act: 2.6368. Min Act: -0.1700
Data Index: 5672015 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7807. Min Range: -2.7807
Max Act: 2.6368. Min Act: -0.1700
Data Index: 2156056 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7807. Min Range: -2.7807
Max Act: 2.6046. Min Act: -0.1700
Data Index: 3682985 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7807. Min Range: -2.7807
Max Act: 2.5563. Min Act: -0.1700
Data Index: 6165343 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7807. Min Range: -2.7807
Max Act: 2.5563. Min Act: -0.1700
Data Index: 662973 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7807. Min Range: -2.7807
Max Act: 2.5885. Min Act: -0.1700
Data Index: 1748253 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7807. Min Range: -2.7807
Max Act: 2.5240. Min Act: -0.1700
Data Index: 6994063 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7807. Min Range: -2.7807
Max Act: 2.5563. Min Act: -0.1700
Data Index: 2279168 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7807. Min Range: -2.7807
Max Act: 2.5078. Min Act: -0.1700
Data Index: 6088815 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7807. Min Range: -2.7807
Max Act: 2.5401. Min Act: -0.1700
Data Index: 5968645 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7807. Min Range: -2.7807
Max Act: 2.5401. Min Act: -0.1700
Data Index: 5467718 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7807. Min Range: -2.7807
Max Act: 2.5401. Min Act: -0.1700
Data Index: 5150002 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19