Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1635 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9768. Min Range: -2.9768
Max Act: 2.9768. Min Act: -0.1700
Data Index: 5203631 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9768. Min Range: -2.9768
Max Act: 2.9293. Min Act: -0.1700
Data Index: 2579889 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9768. Min Range: -2.9768
Max Act: 2.9452. Min Act: -0.1700
Data Index: 2626554 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9768. Min Range: -2.9768
Max Act: 2.9135. Min Act: -0.1700
Data Index: 7807079 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9768. Min Range: -2.9768
Max Act: 2.9135. Min Act: -0.1700
Data Index: 654234 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9768. Min Range: -2.9768
Max Act: 2.8976. Min Act: -0.1700
Data Index: 3166277 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9768. Min Range: -2.9768
Max Act: 2.8818. Min Act: -0.1700
Data Index: 4981959 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9768. Min Range: -2.9768
Max Act: 2.8818. Min Act: -0.1700
Data Index: 8301457 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9768. Min Range: -2.9768
Max Act: 2.8500. Min Act: -0.1700
Data Index: 6558615 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9768. Min Range: -2.9768
Max Act: 2.8659. Min Act: -0.1700
Data Index: 6757786 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9768. Min Range: -2.9768
Max Act: 2.8500. Min Act: -0.1700
Data Index: 2540783 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9768. Min Range: -2.9768
Max Act: 2.8500. Min Act: -0.1700
Data Index: 3466299 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9768. Min Range: -2.9768
Max Act: 2.8659. Min Act: -0.1700
Data Index: 4604540 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9768. Min Range: -2.9768
Max Act: 2.8023. Min Act: -0.1700
Data Index: 2244522 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9768. Min Range: -2.9768
Max Act: 2.7864. Min Act: -0.1700
Data Index: 1890798 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9768. Min Range: -2.9768
Max Act: 2.8023. Min Act: -0.1700
Data Index: 2534411 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9768. Min Range: -2.9768
Max Act: 2.8023. Min Act: -0.1700
Data Index: 2149378 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9768. Min Range: -2.9768
Max Act: 2.7864. Min Act: -0.1700
Data Index: 3316400 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9768. Min Range: -2.9768
Max Act: 2.7864. Min Act: -0.1700
Data Index: 4782807 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9768. Min Range: -2.9768
Max Act: 2.8023. Min Act: -0.1700
Data Index: 1934797 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19