Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3099 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6548. Min Range: -4.6548
Max Act: 4.6548. Min Act: -0.1700
Data Index: 2616833 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6548. Min Range: -4.6548
Max Act: 4.6235. Min Act: -0.1700
Data Index: 111296 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6548. Min Range: -4.6548
Max Act: 4.5610. Min Act: -0.1700
Data Index: 6358187 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6548. Min Range: -4.6548
Max Act: 4.5610. Min Act: -0.1700
Data Index: 7554655 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6548. Min Range: -4.6548
Max Act: 4.5610. Min Act: -0.1700
Data Index: 4219445 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6548. Min Range: -4.6548
Max Act: 4.5610. Min Act: -0.1700
Data Index: 2412174 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6548. Min Range: -4.6548
Max Act: 4.5298. Min Act: -0.1700
Data Index: 6260070 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6548. Min Range: -4.6548
Max Act: 4.5298. Min Act: -0.1700
Data Index: 2581038 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6548. Min Range: -4.6548
Max Act: 4.5298. Min Act: -0.1700
Data Index: 5754398 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6548. Min Range: -4.6548
Max Act: 4.5298. Min Act: -0.1700
Data Index: 5056002 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6548. Min Range: -4.6548
Max Act: 4.5610. Min Act: -0.1700
Data Index: 8660214 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6548. Min Range: -4.6548
Max Act: 4.4985. Min Act: -0.1700
Data Index: 852119 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6548. Min Range: -4.6548
Max Act: 4.5298. Min Act: -0.1700
Data Index: 3699250 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6548. Min Range: -4.6548
Max Act: 4.5298. Min Act: -0.1700
Data Index: 7205701 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6548. Min Range: -4.6548
Max Act: 4.5298. Min Act: -0.1700
Data Index: 582852 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6548. Min Range: -4.6548
Max Act: 4.4985. Min Act: -0.1700
Data Index: 5102502 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6548. Min Range: -4.6548
Max Act: 4.4673. Min Act: -0.1700
Data Index: 5694658 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6548. Min Range: -4.6548
Max Act: 4.4985. Min Act: -0.1700
Data Index: 5834067 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6548. Min Range: -4.6548
Max Act: 4.4985. Min Act: -0.1700
Data Index: 5892951 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6548. Min Range: -4.6548
Max Act: 4.4673. Min Act: -0.1700
Data Index: 26776 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19