Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1054 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8436. Min Range: -3.8436
Max Act: 3.8436. Min Act: -0.1700
Data Index: 1234867 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8436. Min Range: -3.8436
Max Act: 3.8123. Min Act: -0.1700
Data Index: 6438660 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8436. Min Range: -3.8436
Max Act: 3.8436. Min Act: -0.1700
Data Index: 2324142 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8436. Min Range: -3.8436
Max Act: 3.7185. Min Act: -0.1700
Data Index: 4860226 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8436. Min Range: -3.8436
Max Act: 3.7028. Min Act: -0.1700
Data Index: 1112174 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8436. Min Range: -3.8436
Max Act: 3.7028. Min Act: -0.1700
Data Index: 6832692 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8436. Min Range: -3.8436
Max Act: 3.7028. Min Act: -0.1700
Data Index: 3791056 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8436. Min Range: -3.8436
Max Act: 3.6872. Min Act: -0.1700
Data Index: 7842770 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8436. Min Range: -3.8436
Max Act: 3.6559. Min Act: -0.1700
Data Index: 6849057 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8436. Min Range: -3.8436
Max Act: 3.6402. Min Act: -0.1700
Data Index: 7785444 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8436. Min Range: -3.8436
Max Act: 3.6402. Min Act: -0.1700
Data Index: 5605883 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8436. Min Range: -3.8436
Max Act: 3.6246. Min Act: -0.1700
Data Index: 4104154 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8436. Min Range: -3.8436
Max Act: 3.6246. Min Act: -0.1700
Data Index: 666434 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8436. Min Range: -3.8436
Max Act: 3.6246. Min Act: -0.1700
Data Index: 965869 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8436. Min Range: -3.8436
Max Act: 3.6089. Min Act: -0.1700
Data Index: 8412800 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8436. Min Range: -3.8436
Max Act: 3.6089. Min Act: -0.1700
Data Index: 8008741 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8436. Min Range: -3.8436
Max Act: 3.5933. Min Act: -0.1700
Data Index: 2903516 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8436. Min Range: -3.8436
Max Act: 3.5776. Min Act: -0.1700
Data Index: 6739931 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8436. Min Range: -3.8436
Max Act: 3.5933. Min Act: -0.1700
Data Index: 1247035 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8436. Min Range: -3.8436
Max Act: 3.5620. Min Act: -0.1700
Data Index: 3023106 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19