Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3375 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2606. Min Range: -4.2606
Max Act: 4.2294. Min Act: -0.1700
Data Index: 4119293 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2606. Min Range: -4.2606
Max Act: 4.2606. Min Act: -0.1700
Data Index: 295114 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2606. Min Range: -4.2606
Max Act: 4.2294. Min Act: -0.1700
Data Index: 784694 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2606. Min Range: -4.2606
Max Act: 4.2294. Min Act: -0.1700
Data Index: 7274068 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2606. Min Range: -4.2606
Max Act: 4.1669. Min Act: -0.1700
Data Index: 784667 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2606. Min Range: -4.2606
Max Act: 4.1669. Min Act: -0.1700
Data Index: 879749 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2606. Min Range: -4.2606
Max Act: 4.1669. Min Act: -0.1700
Data Index: 6648559 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2606. Min Range: -4.2606
Max Act: 4.1356. Min Act: -0.1700
Data Index: 5584694 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2606. Min Range: -4.2606
Max Act: 4.1669. Min Act: -0.1700
Data Index: 3456453 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2606. Min Range: -4.2606
Max Act: 4.0731. Min Act: -0.1700
Data Index: 7632857 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2606. Min Range: -4.2606
Max Act: 4.1044. Min Act: -0.1700
Data Index: 1886511 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2606. Min Range: -4.2606
Max Act: 4.1669. Min Act: -0.1700
Data Index: 1886523 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2606. Min Range: -4.2606
Max Act: 4.1356. Min Act: -0.1700
Data Index: 6376424 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2606. Min Range: -4.2606
Max Act: 4.1669. Min Act: -0.1700
Data Index: 3466189 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2606. Min Range: -4.2606
Max Act: 4.1044. Min Act: -0.1700
Data Index: 8447270 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2606. Min Range: -4.2606
Max Act: 4.1356. Min Act: -0.1700
Data Index: 665605 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2606. Min Range: -4.2606
Max Act: 4.1356. Min Act: -0.1700
Data Index: 5584693 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2606. Min Range: -4.2606
Max Act: 4.1044. Min Act: -0.1700
Data Index: 6742454 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2606. Min Range: -4.2606
Max Act: 4.0731. Min Act: -0.1700
Data Index: 8447230 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2606. Min Range: -4.2606
Max Act: 4.1044. Min Act: -0.1700
Data Index: 8447239 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19