Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 778 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1673. Min Range: -3.1673
Max Act: 3.1673. Min Act: -0.1700
Data Index: 1414314 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1673. Min Range: -3.1673
Max Act: 2.7078. Min Act: -0.1700
Data Index: 2689651 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1673. Min Range: -3.1673
Max Act: 2.6597. Min Act: -0.1700
Data Index: 1288884 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1673. Min Range: -3.1673
Max Act: 2.6757. Min Act: -0.1700
Data Index: 6012600 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1673. Min Range: -3.1673
Max Act: 2.6276. Min Act: -0.1700
Data Index: 4132207 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1673. Min Range: -3.1673
Max Act: 2.6115. Min Act: -0.1700
Data Index: 330945 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1673. Min Range: -3.1673
Max Act: 2.5632. Min Act: -0.1700
Data Index: 5722288 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1673. Min Range: -3.1673
Max Act: 2.5632. Min Act: -0.1700
Data Index: 7461267 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1673. Min Range: -3.1673
Max Act: 2.5954. Min Act: -0.1700
Data Index: 365749 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1673. Min Range: -3.1673
Max Act: 2.5793. Min Act: -0.1700
Data Index: 8431999 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1673. Min Range: -3.1673
Max Act: 2.6115. Min Act: -0.1700
Data Index: 2804131 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1673. Min Range: -3.1673
Max Act: 2.5632. Min Act: -0.1700
Data Index: 2917897 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1673. Min Range: -3.1673
Max Act: 2.6276. Min Act: -0.1700
Data Index: 91197 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1673. Min Range: -3.1673
Max Act: 2.5632. Min Act: -0.1700
Data Index: 7153165 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1673. Min Range: -3.1673
Max Act: 2.5954. Min Act: -0.1700
Data Index: 8279086 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1673. Min Range: -3.1673
Max Act: 2.5793. Min Act: -0.1700
Data Index: 5025462 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1673. Min Range: -3.1673
Max Act: 2.5471. Min Act: -0.1700
Data Index: 5037484 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1673. Min Range: -3.1673
Max Act: 2.5793. Min Act: -0.1700
Data Index: 1275938 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1673. Min Range: -3.1673
Max Act: 2.5471. Min Act: -0.1700
Data Index: 250199 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1673. Min Range: -3.1673
Max Act: 2.5632. Min Act: -0.1700
Data Index: 5527464 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19