Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3734 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6414. Min Range: -5.6414
Max Act: 5.6414. Min Act: -0.1700
Data Index: 3762920 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6414. Min Range: -5.6414
Max Act: 5.6414. Min Act: -0.1700
Data Index: 1265215 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6414. Min Range: -5.6414
Max Act: 4.5164. Min Act: -0.1700
Data Index: 7662984 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6414. Min Range: -5.6414
Max Act: 4.4539. Min Act: -0.1700
Data Index: 4713080 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6414. Min Range: -5.6414
Max Act: 4.3601. Min Act: -0.1700
Data Index: 177652 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6414. Min Range: -5.6414
Max Act: 4.3601. Min Act: -0.1700
Data Index: 980198 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6414. Min Range: -5.6414
Max Act: 4.3601. Min Act: -0.1700
Data Index: 3951719 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6414. Min Range: -5.6414
Max Act: 4.3289. Min Act: -0.1700
Data Index: 7602467 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6414. Min Range: -5.6414
Max Act: 4.2976. Min Act: -0.1700
Data Index: 4533360 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6414. Min Range: -5.6414
Max Act: 4.3289. Min Act: -0.1700
Data Index: 4948355 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6414. Min Range: -5.6414
Max Act: 4.2976. Min Act: -0.1700
Data Index: 351628 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6414. Min Range: -5.6414
Max Act: 4.2976. Min Act: -0.1700
Data Index: 2557222 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6414. Min Range: -5.6414
Max Act: 4.2664. Min Act: -0.1700
Data Index: 2079552 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6414. Min Range: -5.6414
Max Act: 4.2351. Min Act: -0.1700
Data Index: 4300089 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6414. Min Range: -5.6414
Max Act: 4.2351. Min Act: -0.1700
Data Index: 6883825 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6414. Min Range: -5.6414
Max Act: 4.2351. Min Act: -0.1700
Data Index: 2091749 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6414. Min Range: -5.6414
Max Act: 4.2039. Min Act: -0.1700
Data Index: 2390011 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6414. Min Range: -5.6414
Max Act: 4.2039. Min Act: -0.1700
Data Index: 6885704 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6414. Min Range: -5.6414
Max Act: 4.1726. Min Act: -0.1700
Data Index: 90657 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6414. Min Range: -5.6414
Max Act: 4.1726. Min Act: -0.1700
Data Index: 2319997 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19