Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3777 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2908. Min Range: -6.2908
Max Act: 6.2908. Min Act: -0.1700
Data Index: 4495794 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2908. Min Range: -6.2908
Max Act: 6.2283. Min Act: -0.1700
Data Index: 2807289 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2908. Min Range: -6.2908
Max Act: 6.2283. Min Act: -0.1700
Data Index: 220313 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2908. Min Range: -6.2908
Max Act: 6.2283. Min Act: -0.1700
Data Index: 3914553 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2908. Min Range: -6.2908
Max Act: 6.2283. Min Act: -0.1700
Data Index: 8296992 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2908. Min Range: -6.2908
Max Act: 6.1346. Min Act: -0.1700
Data Index: 376095 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2908. Min Range: -6.2908
Max Act: 6.1658. Min Act: -0.1700
Data Index: 2654001 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2908. Min Range: -6.2908
Max Act: 6.1346. Min Act: -0.1700
Data Index: 8121682 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2908. Min Range: -6.2908
Max Act: 6.1346. Min Act: -0.1700
Data Index: 6724587 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2908. Min Range: -6.2908
Max Act: 6.1033. Min Act: -0.1700
Data Index: 791170 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2908. Min Range: -6.2908
Max Act: 6.1346. Min Act: -0.1700
Data Index: 8615437 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2908. Min Range: -6.2908
Max Act: 6.1033. Min Act: -0.1700
Data Index: 8720566 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2908. Min Range: -6.2908
Max Act: 6.0721. Min Act: -0.1700
Data Index: 710860 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2908. Min Range: -6.2908
Max Act: 6.1033. Min Act: -0.1700
Data Index: 7289572 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2908. Min Range: -6.2908
Max Act: 6.0721. Min Act: -0.1700
Data Index: 7758070 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2908. Min Range: -6.2908
Max Act: 6.0721. Min Act: -0.1700
Data Index: 6537221 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2908. Min Range: -6.2908
Max Act: 6.0721. Min Act: -0.1700
Data Index: 6086657 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2908. Min Range: -6.2908
Max Act: 6.0408. Min Act: -0.1700
Data Index: 4375696 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2908. Min Range: -6.2908
Max Act: 6.0408. Min Act: -0.1700
Data Index: 8377691 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2908. Min Range: -6.2908
Max Act: 6.0408. Min Act: -0.1700
Data Index: 938890 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19