Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1669 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.2401. Min Range: -10.2401
Max Act: 10.2401. Min Act: -0.1700
Data Index: 4985543 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2401. Min Range: -10.2401
Max Act: 10.0526. Min Act: -0.1700
Data Index: 7878600 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2401. Min Range: -10.2401
Max Act: 10.0526. Min Act: -0.1700
Data Index: 7430168 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2401. Min Range: -10.2401
Max Act: 9.9901. Min Act: -0.1700
Data Index: 3496056 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2401. Min Range: -10.2401
Max Act: 9.9901. Min Act: -0.1700
Data Index: 8477671 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2401. Min Range: -10.2401
Max Act: 9.9901. Min Act: -0.1700
Data Index: 5282499 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2401. Min Range: -10.2401
Max Act: 9.8026. Min Act: -0.1700
Data Index: 6360623 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2401. Min Range: -10.2401
Max Act: 9.8026. Min Act: -0.1700
Data Index: 2150796 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2401. Min Range: -10.2401
Max Act: 9.7401. Min Act: -0.1700
Data Index: 5295334 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2401. Min Range: -10.2401
Max Act: 9.6776. Min Act: -0.1700
Data Index: 1842789 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2401. Min Range: -10.2401
Max Act: 9.5526. Min Act: -0.1700
Data Index: 7599763 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2401. Min Range: -10.2401
Max Act: 9.6151. Min Act: -0.1700
Data Index: 4690822 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2401. Min Range: -10.2401
Max Act: 9.6151. Min Act: -0.1700
Data Index: 5414191 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2401. Min Range: -10.2401
Max Act: 9.6151. Min Act: -0.1700
Data Index: 356377 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2401. Min Range: -10.2401
Max Act: 9.6151. Min Act: -0.1700
Data Index: 337342 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2401. Min Range: -10.2401
Max Act: 9.5526. Min Act: -0.1700
Data Index: 7253797 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2401. Min Range: -10.2401
Max Act: 9.4901. Min Act: -0.1700
Data Index: 3902460 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2401. Min Range: -10.2401
Max Act: 9.5526. Min Act: -0.1700
Data Index: 7759239 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2401. Min Range: -10.2401
Max Act: 9.4901. Min Act: -0.1700
Data Index: 7759238 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2401. Min Range: -10.2401
Max Act: 9.3651. Min Act: -0.1700
Data Index: 3386963 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19