Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1635 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0051. Min Range: -5.0051
Max Act: 5.0051. Min Act: -0.1700
Data Index: 6606848 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0051. Min Range: -5.0051
Max Act: 4.5676. Min Act: -0.1700
Data Index: 332468 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0051. Min Range: -5.0051
Max Act: 4.5676. Min Act: -0.1700
Data Index: 332469 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0051. Min Range: -5.0051
Max Act: 4.4738. Min Act: -0.1700
Data Index: 7367438 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0051. Min Range: -5.0051
Max Act: 4.4113. Min Act: -0.1700
Data Index: 332465 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0051. Min Range: -5.0051
Max Act: 4.4738. Min Act: -0.1700
Data Index: 7367442 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0051. Min Range: -5.0051
Max Act: 4.4426. Min Act: -0.1700
Data Index: 2582529 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0051. Min Range: -5.0051
Max Act: 4.4113. Min Act: -0.1700
Data Index: 6606844 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0051. Min Range: -5.0051
Max Act: 4.4113. Min Act: -0.1700
Data Index: 3048954 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0051. Min Range: -5.0051
Max Act: 4.4426. Min Act: -0.1700
Data Index: 5225252 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0051. Min Range: -5.0051
Max Act: 4.4113. Min Act: -0.1700
Data Index: 5225260 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0051. Min Range: -5.0051
Max Act: 4.4113. Min Act: -0.1700
Data Index: 7367432 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0051. Min Range: -5.0051
Max Act: 4.4426. Min Act: -0.1700
Data Index: 7367433 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0051. Min Range: -5.0051
Max Act: 4.4113. Min Act: -0.1700
Data Index: 6606855 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0051. Min Range: -5.0051
Max Act: 4.3488. Min Act: -0.1700
Data Index: 8797592 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0051. Min Range: -5.0051
Max Act: 4.3488. Min Act: -0.1700
Data Index: 1562532 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0051. Min Range: -5.0051
Max Act: 4.3488. Min Act: -0.1700
Data Index: 332475 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0051. Min Range: -5.0051
Max Act: 4.3488. Min Act: -0.1700
Data Index: 6606860 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0051. Min Range: -5.0051
Max Act: 4.2863. Min Act: -0.1700
Data Index: 7367431 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0051. Min Range: -5.0051
Max Act: 4.3176. Min Act: -0.1700
Data Index: 5225257 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19