Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4593 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3559. Min Range: -9.3559
Max Act: 9.3559. Min Act: -0.1700
Data Index: 6865968 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3559. Min Range: -9.3559
Max Act: 8.7309. Min Act: -0.1700
Data Index: 7183984 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3559. Min Range: -9.3559
Max Act: 8.6684. Min Act: -0.1700
Data Index: 6754000 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3559. Min Range: -9.3559
Max Act: 8.4184. Min Act: -0.1700
Data Index: 1918107 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3559. Min Range: -9.3559
Max Act: 8.3559. Min Act: -0.1700
Data Index: 3700602 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3559. Min Range: -9.3559
Max Act: 8.2622. Min Act: -0.1700
Data Index: 155212 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3559. Min Range: -9.3559
Max Act: 8.1997. Min Act: -0.1700
Data Index: 8534216 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3559. Min Range: -9.3559
Max Act: 8.1997. Min Act: -0.1700
Data Index: 6604170 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3559. Min Range: -9.3559
Max Act: 8.1684. Min Act: -0.1700
Data Index: 8171587 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3559. Min Range: -9.3559
Max Act: 8.1684. Min Act: -0.1700
Data Index: 3999701 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3559. Min Range: -9.3559
Max Act: 8.1997. Min Act: -0.1700
Data Index: 2693753 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3559. Min Range: -9.3559
Max Act: 8.1372. Min Act: -0.1700
Data Index: 3640094 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3559. Min Range: -9.3559
Max Act: 8.1372. Min Act: -0.1700
Data Index: 339409 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3559. Min Range: -9.3559
Max Act: 8.1059. Min Act: -0.1700
Data Index: 5558762 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3559. Min Range: -9.3559
Max Act: 8.0434. Min Act: -0.1700
Data Index: 4610870 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3559. Min Range: -9.3559
Max Act: 8.0122. Min Act: -0.1700
Data Index: 7349491 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3559. Min Range: -9.3559
Max Act: 7.9497. Min Act: -0.1700
Data Index: 3412906 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3559. Min Range: -9.3559
Max Act: 7.9809. Min Act: -0.1700
Data Index: 5049908 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3559. Min Range: -9.3559
Max Act: 7.9184. Min Act: -0.1700
Data Index: 4174056 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3559. Min Range: -9.3559
Max Act: 7.9184. Min Act: -0.1700
Data Index: 6785266 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19