Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4559 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4483. Min Range: -5.4483
Max Act: 5.4483. Min Act: -0.1700
Data Index: 6378035 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4483. Min Range: -5.4483
Max Act: 5.2920. Min Act: -0.1700
Data Index: 1846194 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4483. Min Range: -5.4483
Max Act: 5.1358. Min Act: -0.1700
Data Index: 6174971 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4483. Min Range: -5.4483
Max Act: 5.0733. Min Act: -0.1700
Data Index: 4918256 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4483. Min Range: -5.4483
Max Act: 5.0420. Min Act: -0.1700
Data Index: 6174978 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4483. Min Range: -5.4483
Max Act: 5.0733. Min Act: -0.1700
Data Index: 1846195 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4483. Min Range: -5.4483
Max Act: 5.0108. Min Act: -0.1700
Data Index: 6174974 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4483. Min Range: -5.4483
Max Act: 5.0108. Min Act: -0.1700
Data Index: 4599572 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4483. Min Range: -5.4483
Max Act: 4.9795. Min Act: -0.1700
Data Index: 1846196 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4483. Min Range: -5.4483
Max Act: 4.9795. Min Act: -0.1700
Data Index: 4545787 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4483. Min Range: -5.4483
Max Act: 5.0108. Min Act: -0.1700
Data Index: 8213904 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4483. Min Range: -5.4483
Max Act: 4.9483. Min Act: -0.1700
Data Index: 6622416 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4483. Min Range: -5.4483
Max Act: 4.9483. Min Act: -0.1700
Data Index: 4566221 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4483. Min Range: -5.4483
Max Act: 4.9170. Min Act: -0.1700
Data Index: 360134 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4483. Min Range: -5.4483
Max Act: 4.9483. Min Act: -0.1700
Data Index: 6174977 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4483. Min Range: -5.4483
Max Act: 4.9483. Min Act: -0.1700
Data Index: 4346331 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4483. Min Range: -5.4483
Max Act: 4.9483. Min Act: -0.1700
Data Index: 3815798 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4483. Min Range: -5.4483
Max Act: 4.9170. Min Act: -0.1700
Data Index: 1311411 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4483. Min Range: -5.4483
Max Act: 4.9170. Min Act: -0.1700
Data Index: 6313303 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4483. Min Range: -5.4483
Max Act: 4.9170. Min Act: -0.1700
Data Index: 4599561 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19