Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3802 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7639. Min Range: -7.7639
Max Act: 7.7639. Min Act: -0.1700
Data Index: 6949664 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7639. Min Range: -7.7639
Max Act: 7.7014. Min Act: -0.1700
Data Index: 483265 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7639. Min Range: -7.7639
Max Act: 7.6389. Min Act: -0.1700
Data Index: 5240728 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7639. Min Range: -7.7639
Max Act: 7.6389. Min Act: -0.1700
Data Index: 7830062 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7639. Min Range: -7.7639
Max Act: 7.5764. Min Act: -0.1700
Data Index: 5627171 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7639. Min Range: -7.7639
Max Act: 7.5139. Min Act: -0.1700
Data Index: 7895447 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7639. Min Range: -7.7639
Max Act: 7.5451. Min Act: -0.1700
Data Index: 1366282 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7639. Min Range: -7.7639
Max Act: 7.5139. Min Act: -0.1700
Data Index: 5564353 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7639. Min Range: -7.7639
Max Act: 7.4826. Min Act: -0.1700
Data Index: 7190800 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7639. Min Range: -7.7639
Max Act: 7.4514. Min Act: -0.1700
Data Index: 6273344 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7639. Min Range: -7.7639
Max Act: 7.4201. Min Act: -0.1700
Data Index: 7034718 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7639. Min Range: -7.7639
Max Act: 7.3889. Min Act: -0.1700
Data Index: 512130 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7639. Min Range: -7.7639
Max Act: 7.4201. Min Act: -0.1700
Data Index: 2890227 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7639. Min Range: -7.7639
Max Act: 7.3889. Min Act: -0.1700
Data Index: 654819 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7639. Min Range: -7.7639
Max Act: 7.3576. Min Act: -0.1700
Data Index: 4698279 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7639. Min Range: -7.7639
Max Act: 7.2951. Min Act: -0.1700
Data Index: 8697510 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7639. Min Range: -7.7639
Max Act: 7.2639. Min Act: -0.1700
Data Index: 8349546 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7639. Min Range: -7.7639
Max Act: 7.2326. Min Act: -0.1700
Data Index: 4832275 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7639. Min Range: -7.7639
Max Act: 7.2014. Min Act: -0.1700
Data Index: 5805331 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7639. Min Range: -7.7639
Max Act: 7.1701. Min Act: -0.1700
Data Index: 7785563 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19