Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1321 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8401. Min Range: -10.8401
Max Act: 10.8401. Min Act: -0.1700
Data Index: 1628404 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8401. Min Range: -10.8401
Max Act: 10.6526. Min Act: -0.1700
Data Index: 8644376 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8401. Min Range: -10.8401
Max Act: 10.4026. Min Act: -0.1700
Data Index: 3859678 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8401. Min Range: -10.8401
Max Act: 10.2151. Min Act: -0.1700
Data Index: 1569875 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8401. Min Range: -10.8401
Max Act: 10.2151. Min Act: -0.1700
Data Index: 3692783 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8401. Min Range: -10.8401
Max Act: 10.0901. Min Act: -0.1700
Data Index: 7410970 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8401. Min Range: -10.8401
Max Act: 10.0901. Min Act: -0.1700
Data Index: 178230 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8401. Min Range: -10.8401
Max Act: 10.0901. Min Act: -0.1700
Data Index: 3384103 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8401. Min Range: -10.8401
Max Act: 10.0276. Min Act: -0.1700
Data Index: 4631052 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8401. Min Range: -10.8401
Max Act: 10.0276. Min Act: -0.1700
Data Index: 1774153 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8401. Min Range: -10.8401
Max Act: 10.0276. Min Act: -0.1700
Data Index: 8809285 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8401. Min Range: -10.8401
Max Act: 10.0276. Min Act: -0.1700
Data Index: 6410335 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8401. Min Range: -10.8401
Max Act: 9.9651. Min Act: -0.1700
Data Index: 6151326 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8401. Min Range: -10.8401
Max Act: 9.9651. Min Act: -0.1700
Data Index: 1357244 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8401. Min Range: -10.8401
Max Act: 9.8401. Min Act: -0.1700
Data Index: 8160632 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8401. Min Range: -10.8401
Max Act: 9.9026. Min Act: -0.1700
Data Index: 7421991 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8401. Min Range: -10.8401
Max Act: 9.9026. Min Act: -0.1700
Data Index: 8804073 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8401. Min Range: -10.8401
Max Act: 9.9026. Min Act: -0.1700
Data Index: 5796471 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8401. Min Range: -10.8401
Max Act: 9.9026. Min Act: -0.1700
Data Index: 3263486 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8401. Min Range: -10.8401
Max Act: 9.7776. Min Act: -0.1700
Data Index: 2362902 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19