Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2752 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.8431. Min Act: -0.1700
Data Index: 7965000 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.8118. Min Act: -0.1700
Data Index: 3718503 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.5618. Min Act: -0.1700
Data Index: 2854091 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.5618. Min Act: -0.1700
Data Index: 917543 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.4993. Min Act: -0.1700
Data Index: 5168923 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.5306. Min Act: -0.1700
Data Index: 8114913 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.4368. Min Act: -0.1700
Data Index: 3144250 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.4681. Min Act: -0.1700
Data Index: 4057738 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.4368. Min Act: -0.1700
Data Index: 3659014 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.4368. Min Act: -0.1700
Data Index: 1885522 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.3743. Min Act: -0.1700
Data Index: 8277323 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.3431. Min Act: -0.1700
Data Index: 8768167 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.2493. Min Act: -0.1700
Data Index: 4314692 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.2806. Min Act: -0.1700
Data Index: 783616 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.2806. Min Act: -0.1700
Data Index: 2959390 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.2493. Min Act: -0.1700
Data Index: 3616221 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.2493. Min Act: -0.1700
Data Index: 2249794 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.2493. Min Act: -0.1700
Data Index: 1188289 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.2181. Min Act: -0.1700
Data Index: 2556584 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.1868. Min Act: -0.1700
Data Index: 7894090 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19