Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4370 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9154. Min Range: -6.9154
Max Act: 6.9154. Min Act: -0.1700
Data Index: 2157713 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9154. Min Range: -6.9154
Max Act: 6.6967. Min Act: -0.1700
Data Index: 249252 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9154. Min Range: -6.9154
Max Act: 6.6654. Min Act: -0.1700
Data Index: 3225317 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9154. Min Range: -6.9154
Max Act: 6.6029. Min Act: -0.1700
Data Index: 5232202 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9154. Min Range: -6.9154
Max Act: 6.5404. Min Act: -0.1700
Data Index: 6599168 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9154. Min Range: -6.9154
Max Act: 6.5404. Min Act: -0.1700
Data Index: 249255 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9154. Min Range: -6.9154
Max Act: 6.5404. Min Act: -0.1700
Data Index: 1827251 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9154. Min Range: -6.9154
Max Act: 6.5404. Min Act: -0.1700
Data Index: 8737708 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9154. Min Range: -6.9154
Max Act: 6.5092. Min Act: -0.1700
Data Index: 1471609 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9154. Min Range: -6.9154
Max Act: 6.4467. Min Act: -0.1700
Data Index: 1523423 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9154. Min Range: -6.9154
Max Act: 6.4779. Min Act: -0.1700
Data Index: 6975289 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9154. Min Range: -6.9154
Max Act: 6.4779. Min Act: -0.1700
Data Index: 4844263 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9154. Min Range: -6.9154
Max Act: 6.4154. Min Act: -0.1700
Data Index: 3599286 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9154. Min Range: -6.9154
Max Act: 6.4154. Min Act: -0.1700
Data Index: 6621403 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9154. Min Range: -6.9154
Max Act: 6.3842. Min Act: -0.1700
Data Index: 7968915 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9154. Min Range: -6.9154
Max Act: 6.4154. Min Act: -0.1700
Data Index: 4109718 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9154. Min Range: -6.9154
Max Act: 6.3842. Min Act: -0.1700
Data Index: 3225318 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9154. Min Range: -6.9154
Max Act: 6.3842. Min Act: -0.1700
Data Index: 4844262 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9154. Min Range: -6.9154
Max Act: 6.3529. Min Act: -0.1699
Data Index: 2069017 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9154. Min Range: -6.9154
Max Act: 6.3217. Min Act: -0.1700
Data Index: 7865287 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19