Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3074 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9592. Min Range: -5.9592
Max Act: 5.9592. Min Act: -0.1700
Data Index: 4097439 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9592. Min Range: -5.9592
Max Act: 5.8967. Min Act: -0.1700
Data Index: 6215264 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9592. Min Range: -5.9592
Max Act: 5.7717. Min Act: -0.1700
Data Index: 1349952 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9592. Min Range: -5.9592
Max Act: 5.7404. Min Act: -0.1700
Data Index: 6396300 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9592. Min Range: -5.9592
Max Act: 5.7092. Min Act: -0.1700
Data Index: 3519845 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9592. Min Range: -5.9592
Max Act: 5.6154. Min Act: -0.1700
Data Index: 4918478 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9592. Min Range: -5.9592
Max Act: 5.5842. Min Act: -0.1700
Data Index: 6050032 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9592. Min Range: -5.9592
Max Act: 5.5529. Min Act: -0.1700
Data Index: 6459290 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9592. Min Range: -5.9592
Max Act: 5.5217. Min Act: -0.1700
Data Index: 6038236 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9592. Min Range: -5.9592
Max Act: 5.5217. Min Act: -0.1700
Data Index: 1972274 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9592. Min Range: -5.9592
Max Act: 5.5217. Min Act: -0.1700
Data Index: 2470133 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9592. Min Range: -5.9592
Max Act: 5.4904. Min Act: -0.1700
Data Index: 8784021 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9592. Min Range: -5.9592
Max Act: 5.4904. Min Act: -0.1700
Data Index: 7903955 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9592. Min Range: -5.9592
Max Act: 5.4904. Min Act: -0.1700
Data Index: 5317246 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9592. Min Range: -5.9592
Max Act: 5.4592. Min Act: -0.1700
Data Index: 7597359 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9592. Min Range: -5.9592
Max Act: 5.4279. Min Act: -0.1700
Data Index: 4692088 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9592. Min Range: -5.9592
Max Act: 5.3967. Min Act: -0.1700
Data Index: 4408361 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9592. Min Range: -5.9592
Max Act: 5.3654. Min Act: -0.1700
Data Index: 2596233 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9592. Min Range: -5.9592
Max Act: 5.3654. Min Act: -0.1700
Data Index: 788256 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9592. Min Range: -5.9592
Max Act: 5.3654. Min Act: -0.1700
Data Index: 8671045 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19