Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1641 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5653. Min Range: -5.5653
Max Act: 5.5653. Min Act: -0.1700
Data Index: 731428 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5653. Min Range: -5.5653
Max Act: 5.5028. Min Act: -0.1700
Data Index: 8039853 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5653. Min Range: -5.5653
Max Act: 5.4403. Min Act: -0.1700
Data Index: 6717200 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5653. Min Range: -5.5653
Max Act: 5.3778. Min Act: -0.1700
Data Index: 4263840 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5653. Min Range: -5.5653
Max Act: 5.3778. Min Act: -0.1700
Data Index: 5321266 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5653. Min Range: -5.5653
Max Act: 5.3466. Min Act: -0.1700
Data Index: 470459 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5653. Min Range: -5.5653
Max Act: 5.3466. Min Act: -0.1700
Data Index: 7007643 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5653. Min Range: -5.5653
Max Act: 5.2528. Min Act: -0.1700
Data Index: 1009387 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5653. Min Range: -5.5653
Max Act: 5.2216. Min Act: -0.1700
Data Index: 897146 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5653. Min Range: -5.5653
Max Act: 5.1903. Min Act: -0.1700
Data Index: 1373572 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5653. Min Range: -5.5653
Max Act: 5.1903. Min Act: -0.1700
Data Index: 4187683 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5653. Min Range: -5.5653
Max Act: 5.1903. Min Act: -0.1700
Data Index: 5305015 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5653. Min Range: -5.5653
Max Act: 5.1278. Min Act: -0.1700
Data Index: 4149475 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5653. Min Range: -5.5653
Max Act: 5.1278. Min Act: -0.1700
Data Index: 1423224 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5653. Min Range: -5.5653
Max Act: 5.1591. Min Act: -0.1700
Data Index: 6103232 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5653. Min Range: -5.5653
Max Act: 5.1278. Min Act: -0.1700
Data Index: 7413156 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5653. Min Range: -5.5653
Max Act: 5.1591. Min Act: -0.1700
Data Index: 1951922 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5653. Min Range: -5.5653
Max Act: 5.1278. Min Act: -0.1700
Data Index: 4662770 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5653. Min Range: -5.5653
Max Act: 5.0966. Min Act: -0.1700
Data Index: 955828 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5653. Min Range: -5.5653
Max Act: 5.0653. Min Act: -0.1700
Data Index: 3869927 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19