Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4051 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4842. Min Range: -4.4842
Max Act: 4.4842. Min Act: -0.1700
Data Index: 5702370 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4842. Min Range: -4.4842
Max Act: 4.4530. Min Act: -0.1700
Data Index: 7781543 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4842. Min Range: -4.4842
Max Act: 4.4217. Min Act: -0.1700
Data Index: 6094970 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4842. Min Range: -4.4842
Max Act: 4.4530. Min Act: -0.1700
Data Index: 4171232 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4842. Min Range: -4.4842
Max Act: 4.4217. Min Act: -0.1700
Data Index: 1547069 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4842. Min Range: -4.4842
Max Act: 4.4217. Min Act: -0.1700
Data Index: 7752767 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4842. Min Range: -4.4842
Max Act: 4.4217. Min Act: -0.1700
Data Index: 1249462 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4842. Min Range: -4.4842
Max Act: 4.3592. Min Act: -0.1700
Data Index: 6703557 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4842. Min Range: -4.4842
Max Act: 4.3592. Min Act: -0.1700
Data Index: 905530 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4842. Min Range: -4.4842
Max Act: 4.3280. Min Act: -0.1700
Data Index: 6863005 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4842. Min Range: -4.4842
Max Act: 4.3280. Min Act: -0.1700
Data Index: 8828385 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4842. Min Range: -4.4842
Max Act: 4.2967. Min Act: -0.1700
Data Index: 8822285 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4842. Min Range: -4.4842
Max Act: 4.3280. Min Act: -0.1700
Data Index: 4889367 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4842. Min Range: -4.4842
Max Act: 4.3280. Min Act: -0.1700
Data Index: 657690 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4842. Min Range: -4.4842
Max Act: 4.3280. Min Act: -0.1700
Data Index: 121929 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4842. Min Range: -4.4842
Max Act: 4.2967. Min Act: -0.1700
Data Index: 5748912 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4842. Min Range: -4.4842
Max Act: 4.2655. Min Act: -0.1700
Data Index: 6655659 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4842. Min Range: -4.4842
Max Act: 4.2967. Min Act: -0.1700
Data Index: 4569796 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4842. Min Range: -4.4842
Max Act: 4.2655. Min Act: -0.1700
Data Index: 4662766 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4842. Min Range: -4.4842
Max Act: 4.2967. Min Act: -0.1700
Data Index: 2024020 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19