Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4303 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3338. Min Range: -7.3338
Max Act: 7.3338. Min Act: -0.1700
Data Index: 1841007 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3338. Min Range: -7.3338
Max Act: 7.1463. Min Act: -0.1700
Data Index: 3988313 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3338. Min Range: -7.3338
Max Act: 6.9901. Min Act: -0.1700
Data Index: 5771660 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3338. Min Range: -7.3338
Max Act: 6.9901. Min Act: -0.1700
Data Index: 7689498 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3338. Min Range: -7.3338
Max Act: 6.9276. Min Act: -0.1700
Data Index: 4551949 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3338. Min Range: -7.3338
Max Act: 6.8963. Min Act: -0.1700
Data Index: 4330039 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3338. Min Range: -7.3338
Max Act: 6.8963. Min Act: -0.1700
Data Index: 6781758 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3338. Min Range: -7.3338
Max Act: 6.8963. Min Act: -0.1700
Data Index: 2372488 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3338. Min Range: -7.3338
Max Act: 6.8963. Min Act: -0.1700
Data Index: 3631297 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3338. Min Range: -7.3338
Max Act: 6.8651. Min Act: -0.1700
Data Index: 35119 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3338. Min Range: -7.3338
Max Act: 6.8338. Min Act: -0.1700
Data Index: 8602386 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3338. Min Range: -7.3338
Max Act: 6.8338. Min Act: -0.1700
Data Index: 7324401 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3338. Min Range: -7.3338
Max Act: 6.7401. Min Act: -0.1700
Data Index: 4090751 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3338. Min Range: -7.3338
Max Act: 6.7401. Min Act: -0.1700
Data Index: 7636232 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3338. Min Range: -7.3338
Max Act: 6.7401. Min Act: -0.1700
Data Index: 5608536 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3338. Min Range: -7.3338
Max Act: 6.6776. Min Act: -0.1700
Data Index: 924771 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3338. Min Range: -7.3338
Max Act: 6.6776. Min Act: -0.1700
Data Index: 1141644 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3338. Min Range: -7.3338
Max Act: 6.6463. Min Act: -0.1700
Data Index: 4114846 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3338. Min Range: -7.3338
Max Act: 6.6151. Min Act: -0.1700
Data Index: 4683524 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3338. Min Range: -7.3338
Max Act: 6.6776. Min Act: -0.1700
Data Index: 2484182 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19