Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1908 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.3772. Min Act: -0.1700
Data Index: 5585901 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.3147. Min Act: -0.1700
Data Index: 8266416 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.2522. Min Act: -0.1700
Data Index: 796826 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.2210. Min Act: -0.1700
Data Index: 8545308 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1897. Min Act: -0.1700
Data Index: 2531138 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1897. Min Act: -0.1700
Data Index: 3056634 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1897. Min Act: -0.1700
Data Index: 4161259 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1897. Min Act: -0.1700
Data Index: 1710011 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1897. Min Act: -0.1700
Data Index: 4194239 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1897. Min Act: -0.1700
Data Index: 4127079 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1897. Min Act: -0.1700
Data Index: 304061 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1272. Min Act: -0.1700
Data Index: 4945659 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1585. Min Act: -0.1700
Data Index: 4352096 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1585. Min Act: -0.1700
Data Index: 144435 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1585. Min Act: -0.1700
Data Index: 671673 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1272. Min Act: -0.1700
Data Index: 15100 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1272. Min Act: -0.1700
Data Index: 6086504 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1272. Min Act: -0.1700
Data Index: 6424279 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.1272. Min Act: -0.1700
Data Index: 6442311 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3772. Min Range: -4.3772
Max Act: 4.0959. Min Act: -0.1700
Data Index: 4772738 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19