Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4231 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4625. Min Range: -4.4625
Max Act: 4.4625. Min Act: -0.1700
Data Index: 3362795 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4625. Min Range: -4.4625
Max Act: 4.4625. Min Act: -0.1700
Data Index: 3462707 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4625. Min Range: -4.4625
Max Act: 4.4625. Min Act: -0.1700
Data Index: 444810 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4625. Min Range: -4.4625
Max Act: 4.4313. Min Act: -0.1700
Data Index: 8189869 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4625. Min Range: -4.4625
Max Act: 4.4000. Min Act: -0.1700
Data Index: 8160297 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4625. Min Range: -4.4625
Max Act: 4.3688. Min Act: -0.1700
Data Index: 7656552 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4625. Min Range: -4.4625
Max Act: 4.3375. Min Act: -0.1700
Data Index: 3017679 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4625. Min Range: -4.4625
Max Act: 4.3375. Min Act: -0.1700
Data Index: 2449292 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4625. Min Range: -4.4625
Max Act: 4.3375. Min Act: -0.1700
Data Index: 323857 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4625. Min Range: -4.4625
Max Act: 4.3688. Min Act: -0.1700
Data Index: 2135185 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4625. Min Range: -4.4625
Max Act: 4.3375. Min Act: -0.1700
Data Index: 8507076 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4625. Min Range: -4.4625
Max Act: 4.3063. Min Act: -0.1700
Data Index: 6794465 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4625. Min Range: -4.4625
Max Act: 4.2750. Min Act: -0.1700
Data Index: 5948592 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4625. Min Range: -4.4625
Max Act: 4.2750. Min Act: -0.1700
Data Index: 1292419 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4625. Min Range: -4.4625
Max Act: 4.2438. Min Act: -0.1700
Data Index: 8759724 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4625. Min Range: -4.4625
Max Act: 4.2750. Min Act: -0.1700
Data Index: 3547594 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4625. Min Range: -4.4625
Max Act: 4.2750. Min Act: -0.1700
Data Index: 5002676 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4625. Min Range: -4.4625
Max Act: 4.2750. Min Act: -0.1700
Data Index: 462401 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4625. Min Range: -4.4625
Max Act: 4.2750. Min Act: -0.1700
Data Index: 1638110 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4625. Min Range: -4.4625
Max Act: 4.2750. Min Act: -0.1700
Data Index: 222897 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19