Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2072. Min Range: -5.2072
Max Act: 5.2072. Min Act: -0.1700
Data Index: 947514 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2072. Min Range: -5.2072
Max Act: 4.7072. Min Act: -0.1700
Data Index: 6360378 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2072. Min Range: -5.2072
Max Act: 4.5822. Min Act: -0.1700
Data Index: 2589231 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2072. Min Range: -5.2072
Max Act: 4.5822. Min Act: -0.1700
Data Index: 3374768 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2072. Min Range: -5.2072
Max Act: 4.5822. Min Act: -0.1700
Data Index: 5934395 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2072. Min Range: -5.2072
Max Act: 4.5510. Min Act: -0.1700
Data Index: 4611341 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2072. Min Range: -5.2072
Max Act: 4.4572. Min Act: -0.1700
Data Index: 7154808 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2072. Min Range: -5.2072
Max Act: 4.4572. Min Act: -0.1700
Data Index: 5627411 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2072. Min Range: -5.2072
Max Act: 4.4260. Min Act: -0.1700
Data Index: 5767977 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2072. Min Range: -5.2072
Max Act: 4.4260. Min Act: -0.1700
Data Index: 480059 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2072. Min Range: -5.2072
Max Act: 4.4260. Min Act: -0.1700
Data Index: 4670820 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2072. Min Range: -5.2072
Max Act: 4.3947. Min Act: -0.1700
Data Index: 5811854 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2072. Min Range: -5.2072
Max Act: 4.3947. Min Act: -0.1700
Data Index: 6923592 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2072. Min Range: -5.2072
Max Act: 4.3635. Min Act: -0.1700
Data Index: 17193 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2072. Min Range: -5.2072
Max Act: 4.3635. Min Act: -0.1700
Data Index: 1986716 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2072. Min Range: -5.2072
Max Act: 4.3635. Min Act: -0.1700
Data Index: 727135 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2072. Min Range: -5.2072
Max Act: 4.3635. Min Act: -0.1700
Data Index: 4572606 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2072. Min Range: -5.2072
Max Act: 4.3322. Min Act: -0.1700
Data Index: 5615848 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2072. Min Range: -5.2072
Max Act: 4.3322. Min Act: -0.1700
Data Index: 499934 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2072. Min Range: -5.2072
Max Act: 4.3322. Min Act: -0.1700
Data Index: 4523485 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19