Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2810 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1360. Min Range: -7.1360
Max Act: 7.1360. Min Act: -0.1700
Data Index: 6356235 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1360. Min Range: -7.1360
Max Act: 7.1047. Min Act: -0.1700
Data Index: 5096306 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1360. Min Range: -7.1360
Max Act: 6.9485. Min Act: -0.1700
Data Index: 3507820 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1360. Min Range: -7.1360
Max Act: 6.9485. Min Act: -0.1700
Data Index: 1999966 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1360. Min Range: -7.1360
Max Act: 6.8235. Min Act: -0.1700
Data Index: 8318431 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1360. Min Range: -7.1360
Max Act: 6.7922. Min Act: -0.1700
Data Index: 1184115 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1360. Min Range: -7.1360
Max Act: 6.6985. Min Act: -0.1700
Data Index: 4071002 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1360. Min Range: -7.1360
Max Act: 6.7297. Min Act: -0.1700
Data Index: 329507 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1360. Min Range: -7.1360
Max Act: 6.6985. Min Act: -0.1700
Data Index: 718642 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1360. Min Range: -7.1360
Max Act: 6.6047. Min Act: -0.1700
Data Index: 7553819 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1360. Min Range: -7.1360
Max Act: 6.5110. Min Act: -0.1700
Data Index: 7673301 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1360. Min Range: -7.1360
Max Act: 6.5110. Min Act: -0.1700
Data Index: 1726147 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1360. Min Range: -7.1360
Max Act: 6.4485. Min Act: -0.1700
Data Index: 1786089 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1360. Min Range: -7.1360
Max Act: 6.4172. Min Act: -0.1700
Data Index: 8363863 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1360. Min Range: -7.1360
Max Act: 6.4172. Min Act: -0.1700
Data Index: 3194512 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1360. Min Range: -7.1360
Max Act: 6.3860. Min Act: -0.1700
Data Index: 352825 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1360. Min Range: -7.1360
Max Act: 6.3860. Min Act: -0.1700
Data Index: 1849282 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1360. Min Range: -7.1360
Max Act: 6.3860. Min Act: -0.1700
Data Index: 1169261 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1360. Min Range: -7.1360
Max Act: 6.3547. Min Act: -0.1700
Data Index: 3347941 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1360. Min Range: -7.1360
Max Act: 6.3547. Min Act: -0.1700
Data Index: 4264388 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19