Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3254 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4156. Min Range: -6.4156
Max Act: 6.4156. Min Act: -0.1700
Data Index: 8559305 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4156. Min Range: -6.4156
Max Act: 6.2593. Min Act: -0.1700
Data Index: 6385203 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4156. Min Range: -6.4156
Max Act: 6.2906. Min Act: -0.1700
Data Index: 6385199 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4156. Min Range: -6.4156
Max Act: 6.2593. Min Act: -0.1700
Data Index: 165442 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4156. Min Range: -6.4156
Max Act: 6.2281. Min Act: -0.1700
Data Index: 2305112 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4156. Min Range: -6.4156
Max Act: 6.2281. Min Act: -0.1700
Data Index: 2003949 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4156. Min Range: -6.4156
Max Act: 6.1656. Min Act: -0.1700
Data Index: 2305118 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4156. Min Range: -6.4156
Max Act: 6.1343. Min Act: -0.1700
Data Index: 5912297 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4156. Min Range: -6.4156
Max Act: 6.0718. Min Act: -0.1700
Data Index: 2078378 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4156. Min Range: -6.4156
Max Act: 6.0406. Min Act: -0.1700
Data Index: 3043423 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4156. Min Range: -6.4156
Max Act: 6.0406. Min Act: -0.1700
Data Index: 8571924 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4156. Min Range: -6.4156
Max Act: 6.0406. Min Act: -0.1700
Data Index: 7775968 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4156. Min Range: -6.4156
Max Act: 6.0406. Min Act: -0.1700
Data Index: 7304535 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4156. Min Range: -6.4156
Max Act: 6.0406. Min Act: -0.1700
Data Index: 6433902 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4156. Min Range: -6.4156
Max Act: 6.0093. Min Act: -0.1700
Data Index: 4985489 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4156. Min Range: -6.4156
Max Act: 6.0093. Min Act: -0.1700
Data Index: 7304538 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4156. Min Range: -6.4156
Max Act: 6.0093. Min Act: -0.1700
Data Index: 6385207 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4156. Min Range: -6.4156
Max Act: 5.9781. Min Act: -0.1700
Data Index: 3043425 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4156. Min Range: -6.4156
Max Act: 5.9468. Min Act: -0.1700
Data Index: 3953352 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4156. Min Range: -6.4156
Max Act: 5.9468. Min Act: -0.1700
Data Index: 1669914 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19