Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2430 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7723. Min Range: -3.7723
Max Act: 3.7723. Min Act: -0.1700
Data Index: 4226720 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7723. Min Range: -3.7723
Max Act: 3.7097. Min Act: -0.1700
Data Index: 2722963 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7723. Min Range: -3.7723
Max Act: 3.7410. Min Act: -0.1700
Data Index: 4451119 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7723. Min Range: -3.7723
Max Act: 3.7410. Min Act: -0.1700
Data Index: 8068670 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7723. Min Range: -3.7723
Max Act: 3.7097. Min Act: -0.1700
Data Index: 7951526 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7723. Min Range: -3.7723
Max Act: 3.7097. Min Act: -0.1700
Data Index: 4166107 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7723. Min Range: -3.7723
Max Act: 3.6785. Min Act: -0.1700
Data Index: 6195246 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7723. Min Range: -3.7723
Max Act: 3.6785. Min Act: -0.1700
Data Index: 443693 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7723. Min Range: -3.7723
Max Act: 3.6785. Min Act: -0.1700
Data Index: 7062640 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7723. Min Range: -3.7723
Max Act: 3.5846. Min Act: -0.1700
Data Index: 2124991 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7723. Min Range: -3.7723
Max Act: 3.6472. Min Act: -0.1700
Data Index: 4684435 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7723. Min Range: -3.7723
Max Act: 3.6472. Min Act: -0.1700
Data Index: 2143234 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7723. Min Range: -3.7723
Max Act: 3.6472. Min Act: -0.1700
Data Index: 666473 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7723. Min Range: -3.7723
Max Act: 3.6472. Min Act: -0.1700
Data Index: 1736600 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7723. Min Range: -3.7723
Max Act: 3.6472. Min Act: -0.1700
Data Index: 6767593 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7723. Min Range: -3.7723
Max Act: 3.6472. Min Act: -0.1700
Data Index: 4698262 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7723. Min Range: -3.7723
Max Act: 3.6159. Min Act: -0.1700
Data Index: 308763 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7723. Min Range: -3.7723
Max Act: 3.5846. Min Act: -0.1700
Data Index: 3875037 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7723. Min Range: -3.7723
Max Act: 3.6472. Min Act: -0.1700
Data Index: 3022948 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7723. Min Range: -3.7723
Max Act: 3.5846. Min Act: -0.1700
Data Index: 92190 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19