Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4091 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5369. Min Range: -3.5369
Max Act: 3.5369. Min Act: -0.1700
Data Index: 3793004 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5369. Min Range: -3.5369
Max Act: 3.4743. Min Act: -0.1700
Data Index: 8677853 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5369. Min Range: -3.5369
Max Act: 3.4429. Min Act: -0.1700
Data Index: 7292441 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5369. Min Range: -3.5369
Max Act: 3.4116. Min Act: -0.1700
Data Index: 7436108 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5369. Min Range: -3.5369
Max Act: 3.3802. Min Act: -0.1700
Data Index: 7849584 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5369. Min Range: -3.5369
Max Act: 3.3959. Min Act: -0.1700
Data Index: 186323 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5369. Min Range: -3.5369
Max Act: 3.3489. Min Act: -0.1700
Data Index: 4778071 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5369. Min Range: -3.5369
Max Act: 3.3802. Min Act: -0.1700
Data Index: 1885075 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5369. Min Range: -3.5369
Max Act: 3.3645. Min Act: -0.1700
Data Index: 8454678 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5369. Min Range: -3.5369
Max Act: 3.3489. Min Act: -0.1700
Data Index: 1117776 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5369. Min Range: -3.5369
Max Act: 3.3175. Min Act: -0.1700
Data Index: 6513638 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5369. Min Range: -3.5369
Max Act: 3.3175. Min Act: -0.1700
Data Index: 1940108 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5369. Min Range: -3.5369
Max Act: 3.3175. Min Act: -0.1700
Data Index: 781757 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5369. Min Range: -3.5369
Max Act: 3.2861. Min Act: -0.1700
Data Index: 3361023 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5369. Min Range: -3.5369
Max Act: 3.2704. Min Act: -0.1700
Data Index: 2762918 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5369. Min Range: -3.5369
Max Act: 3.2861. Min Act: -0.1700
Data Index: 3555893 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5369. Min Range: -3.5369
Max Act: 3.3175. Min Act: -0.1700
Data Index: 8400216 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5369. Min Range: -3.5369
Max Act: 3.2861. Min Act: -0.1700
Data Index: 1753027 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5369. Min Range: -3.5369
Max Act: 3.2704. Min Act: -0.1700
Data Index: 8491561 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5369. Min Range: -3.5369
Max Act: 3.2390. Min Act: -0.1700
Data Index: 6582412 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19