Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2230 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0682. Min Range: -4.0682
Max Act: 4.0682. Min Act: -0.1700
Data Index: 3339241 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0682. Min Range: -4.0682
Max Act: 4.0370. Min Act: -0.1700
Data Index: 7899164 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0682. Min Range: -4.0682
Max Act: 4.0370. Min Act: -0.1700
Data Index: 864264 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0682. Min Range: -4.0682
Max Act: 4.0057. Min Act: -0.1700
Data Index: 7588678 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0682. Min Range: -4.0682
Max Act: 4.0370. Min Act: -0.1700
Data Index: 1631916 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0682. Min Range: -4.0682
Max Act: 3.9745. Min Act: -0.1700
Data Index: 8800095 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0682. Min Range: -4.0682
Max Act: 4.0057. Min Act: -0.1700
Data Index: 3699752 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0682. Min Range: -4.0682
Max Act: 3.9432. Min Act: -0.1700
Data Index: 7962562 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0682. Min Range: -4.0682
Max Act: 3.9432. Min Act: -0.1700
Data Index: 7692111 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0682. Min Range: -4.0682
Max Act: 3.8807. Min Act: -0.1700
Data Index: 6888021 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0682. Min Range: -4.0682
Max Act: 3.9119. Min Act: -0.1700
Data Index: 4194642 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0682. Min Range: -4.0682
Max Act: 3.8494. Min Act: -0.1700
Data Index: 8405889 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0682. Min Range: -4.0682
Max Act: 3.8807. Min Act: -0.1700
Data Index: 3416991 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0682. Min Range: -4.0682
Max Act: 3.8494. Min Act: -0.1700
Data Index: 4461657 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0682. Min Range: -4.0682
Max Act: 3.8181. Min Act: -0.1700
Data Index: 6905385 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0682. Min Range: -4.0682
Max Act: 3.8181. Min Act: -0.1700
Data Index: 1659018 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0682. Min Range: -4.0682
Max Act: 3.8181. Min Act: -0.1700
Data Index: 2764533 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0682. Min Range: -4.0682
Max Act: 3.7869. Min Act: -0.1700
Data Index: 841366 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0682. Min Range: -4.0682
Max Act: 3.7869. Min Act: -0.1700
Data Index: 1164901 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0682. Min Range: -4.0682
Max Act: 3.7556. Min Act: -0.1700
Data Index: 4569524 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19