Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2421 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2130. Min Range: -6.2130
Max Act: 6.2130. Min Act: -0.1700
Data Index: 8355862 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2130. Min Range: -6.2130
Max Act: 5.8380. Min Act: -0.1700
Data Index: 2686999 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2130. Min Range: -6.2130
Max Act: 5.8380. Min Act: -0.1700
Data Index: 1405867 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2130. Min Range: -6.2130
Max Act: 5.7130. Min Act: -0.1700
Data Index: 7807335 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2130. Min Range: -6.2130
Max Act: 4.6505. Min Act: -0.1700
Data Index: 6277333 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2130. Min Range: -6.2130
Max Act: 5.4630. Min Act: -0.1700
Data Index: 458421 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2130. Min Range: -6.2130
Max Act: 5.8693. Min Act: -0.1700
Data Index: 4562730 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2130. Min Range: -6.2130
Max Act: 5.6505. Min Act: -0.1700
Data Index: 1271003 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2130. Min Range: -6.2130
Max Act: 5.5880. Min Act: -0.1700
Data Index: 8664292 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2130. Min Range: -6.2130
Max Act: 5.5880. Min Act: -0.1700
Data Index: 3441906 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2130. Min Range: -6.2130
Max Act: 5.4943. Min Act: -0.1700
Data Index: 3948388 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2130. Min Range: -6.2130
Max Act: 5.4630. Min Act: -0.1700
Data Index: 1786324 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2130. Min Range: -6.2130
Max Act: 5.4630. Min Act: -0.1700
Data Index: 1641604 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2130. Min Range: -6.2130
Max Act: 5.4005. Min Act: -0.1700
Data Index: 91146 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2130. Min Range: -6.2130
Max Act: 5.4318. Min Act: -0.1700
Data Index: 5011220 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2130. Min Range: -6.2130
Max Act: 5.4630. Min Act: -0.1700
Data Index: 2689197 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2130. Min Range: -6.2130
Max Act: 5.4005. Min Act: -0.1700
Data Index: 6978413 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2130. Min Range: -6.2130
Max Act: 4.6505. Min Act: -0.1700
Data Index: 6349355 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2130. Min Range: -6.2130
Max Act: 5.4005. Min Act: -0.1700
Data Index: 4785434 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2130. Min Range: -6.2130
Max Act: 5.4943. Min Act: -0.1700
Data Index: 3149821 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19