Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 694 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1572. Min Range: -6.1572
Max Act: 6.1572. Min Act: -0.1700
Data Index: 1242133 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1572. Min Range: -6.1572
Max Act: 6.0322. Min Act: -0.1700
Data Index: 4831221 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1572. Min Range: -6.1572
Max Act: 5.9697. Min Act: -0.1700
Data Index: 7890396 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1572. Min Range: -6.1572
Max Act: 5.9072. Min Act: -0.1700
Data Index: 4789432 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1572. Min Range: -6.1572
Max Act: 5.9385. Min Act: -0.1700
Data Index: 2499997 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1572. Min Range: -6.1572
Max Act: 5.9385. Min Act: -0.1700
Data Index: 1273709 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1572. Min Range: -6.1572
Max Act: 5.9072. Min Act: -0.1700
Data Index: 2367526 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1572. Min Range: -6.1572
Max Act: 5.8760. Min Act: -0.1700
Data Index: 3415502 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1572. Min Range: -6.1572
Max Act: 5.9072. Min Act: -0.1700
Data Index: 5118600 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1572. Min Range: -6.1572
Max Act: 5.8760. Min Act: -0.1700
Data Index: 7916194 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1572. Min Range: -6.1572
Max Act: 5.8760. Min Act: -0.1700
Data Index: 777460 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1572. Min Range: -6.1572
Max Act: 5.8760. Min Act: -0.1700
Data Index: 7019407 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1572. Min Range: -6.1572
Max Act: 5.9072. Min Act: -0.1700
Data Index: 6104446 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1572. Min Range: -6.1572
Max Act: 5.8760. Min Act: -0.1700
Data Index: 520543 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1572. Min Range: -6.1572
Max Act: 5.8447. Min Act: -0.1700
Data Index: 3439955 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1572. Min Range: -6.1572
Max Act: 5.8760. Min Act: -0.1700
Data Index: 4183360 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1572. Min Range: -6.1572
Max Act: 5.8447. Min Act: -0.1700
Data Index: 5230554 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1572. Min Range: -6.1572
Max Act: 5.8447. Min Act: -0.1700
Data Index: 8083243 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1572. Min Range: -6.1572
Max Act: 5.8135. Min Act: -0.1700
Data Index: 8048336 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1572. Min Range: -6.1572
Max Act: 5.7822. Min Act: -0.1700
Data Index: 5878490 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19