Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3008 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9512. Min Range: -2.9512
Max Act: 2.9512. Min Act: -0.1700
Data Index: 759283 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9512. Min Range: -2.9512
Max Act: 2.7924. Min Act: -0.1700
Data Index: 3713252 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9512. Min Range: -2.9512
Max Act: 2.7445. Min Act: -0.1700
Data Index: 2530901 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9512. Min Range: -2.9512
Max Act: 2.7286. Min Act: -0.1700
Data Index: 6463160 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9512. Min Range: -2.9512
Max Act: 2.7286. Min Act: -0.1700
Data Index: 2057300 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9512. Min Range: -2.9512
Max Act: 2.7286. Min Act: -0.1700
Data Index: 525945 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9512. Min Range: -2.9512
Max Act: 2.7126. Min Act: -0.1700
Data Index: 2530900 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9512. Min Range: -2.9512
Max Act: 2.6966. Min Act: -0.1700
Data Index: 5726221 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9512. Min Range: -2.9512
Max Act: 2.7126. Min Act: -0.1700
Data Index: 2057298 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9512. Min Range: -2.9512
Max Act: 2.6806. Min Act: -0.1700
Data Index: 2405941 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9512. Min Range: -2.9512
Max Act: 2.6966. Min Act: -0.1700
Data Index: 1902353 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9512. Min Range: -2.9512
Max Act: 2.6966. Min Act: -0.1700
Data Index: 4520963 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9512. Min Range: -2.9512
Max Act: 2.6806. Min Act: -0.1700
Data Index: 6942168 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9512. Min Range: -2.9512
Max Act: 2.6646. Min Act: -0.1700
Data Index: 8053670 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9512. Min Range: -2.9512
Max Act: 2.6806. Min Act: -0.1700
Data Index: 3823397 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9512. Min Range: -2.9512
Max Act: 2.6646. Min Act: -0.1700
Data Index: 779051 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9512. Min Range: -2.9512
Max Act: 2.6485. Min Act: -0.1700
Data Index: 538452 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9512. Min Range: -2.9512
Max Act: 2.6646. Min Act: -0.1700
Data Index: 5496318 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9512. Min Range: -2.9512
Max Act: 2.6485. Min Act: -0.1700
Data Index: 1767054 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9512. Min Range: -2.9512
Max Act: 2.6325. Min Act: -0.1700
Data Index: 3325297 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19