Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3656 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6225. Min Range: -7.6225
Max Act: 7.6225. Min Act: -0.1700
Data Index: 6675384 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6225. Min Range: -7.6225
Max Act: 7.5912. Min Act: -0.1700
Data Index: 909276 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6225. Min Range: -7.6225
Max Act: 7.5287. Min Act: -0.1700
Data Index: 5490433 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6225. Min Range: -7.6225
Max Act: 7.4975. Min Act: -0.1700
Data Index: 3090063 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6225. Min Range: -7.6225
Max Act: 7.4662. Min Act: -0.1700
Data Index: 235781 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6225. Min Range: -7.6225
Max Act: 7.4350. Min Act: -0.1700
Data Index: 5103855 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6225. Min Range: -7.6225
Max Act: 7.4350. Min Act: -0.1700
Data Index: 1994641 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6225. Min Range: -7.6225
Max Act: 7.4037. Min Act: -0.1700
Data Index: 485457 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6225. Min Range: -7.6225
Max Act: 7.4037. Min Act: -0.1700
Data Index: 4877897 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6225. Min Range: -7.6225
Max Act: 7.4037. Min Act: -0.1700
Data Index: 6743691 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6225. Min Range: -7.6225
Max Act: 7.3725. Min Act: -0.1700
Data Index: 3455294 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6225. Min Range: -7.6225
Max Act: 7.4037. Min Act: -0.1700
Data Index: 1266131 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6225. Min Range: -7.6225
Max Act: 7.3725. Min Act: -0.1700
Data Index: 4956289 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6225. Min Range: -7.6225
Max Act: 7.3412. Min Act: -0.1700
Data Index: 3749970 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6225. Min Range: -7.6225
Max Act: 7.3412. Min Act: -0.1700
Data Index: 577601 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6225. Min Range: -7.6225
Max Act: 7.3412. Min Act: -0.1700
Data Index: 2960645 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6225. Min Range: -7.6225
Max Act: 7.3412. Min Act: -0.1700
Data Index: 2683020 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6225. Min Range: -7.6225
Max Act: 7.3412. Min Act: -0.1700
Data Index: 5569599 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6225. Min Range: -7.6225
Max Act: 7.3412. Min Act: -0.1700
Data Index: 5558504 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6225. Min Range: -7.6225
Max Act: 7.3412. Min Act: -0.1700
Data Index: 3300746 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19