Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1231 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1439. Min Range: -7.1439
Max Act: 7.1439. Min Act: -0.1700
Data Index: 7078716 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1439. Min Range: -7.1439
Max Act: 6.8939. Min Act: -0.1700
Data Index: 7394200 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1439. Min Range: -7.1439
Max Act: 6.8626. Min Act: -0.1700
Data Index: 3874688 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1439. Min Range: -7.1439
Max Act: 6.7376. Min Act: -0.1700
Data Index: 6679432 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1439. Min Range: -7.1439
Max Act: 6.6751. Min Act: -0.1700
Data Index: 1839211 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1439. Min Range: -7.1439
Max Act: 6.6751. Min Act: -0.1700
Data Index: 1416620 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1439. Min Range: -7.1439
Max Act: 6.6439. Min Act: -0.1700
Data Index: 8550805 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1439. Min Range: -7.1439
Max Act: 6.6439. Min Act: -0.1700
Data Index: 6141443 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1439. Min Range: -7.1439
Max Act: 6.6126. Min Act: -0.1700
Data Index: 7437864 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1439. Min Range: -7.1439
Max Act: 6.5501. Min Act: -0.1700
Data Index: 3838128 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1439. Min Range: -7.1439
Max Act: 6.5501. Min Act: -0.1700
Data Index: 513892 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1439. Min Range: -7.1439
Max Act: 6.5814. Min Act: -0.1700
Data Index: 5153702 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1439. Min Range: -7.1439
Max Act: 6.5501. Min Act: -0.1700
Data Index: 1600401 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1439. Min Range: -7.1439
Max Act: 6.5501. Min Act: -0.1700
Data Index: 6673564 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1439. Min Range: -7.1439
Max Act: 6.5189. Min Act: -0.1700
Data Index: 4088999 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1439. Min Range: -7.1439
Max Act: 6.5189. Min Act: -0.1700
Data Index: 6434970 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1439. Min Range: -7.1439
Max Act: 6.5189. Min Act: -0.1700
Data Index: 7375457 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1439. Min Range: -7.1439
Max Act: 6.5189. Min Act: -0.1700
Data Index: 4641354 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1439. Min Range: -7.1439
Max Act: 6.4564. Min Act: -0.1700
Data Index: 1908442 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1439. Min Range: -7.1439
Max Act: 6.4876. Min Act: -0.1700
Data Index: 3651605 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19