Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3784 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0436. Min Range: -5.0436
Max Act: 5.0436. Min Act: -0.1700
Data Index: 7733900 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0436. Min Range: -5.0436
Max Act: 5.0123. Min Act: -0.1700
Data Index: 756785 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0436. Min Range: -5.0436
Max Act: 5.0436. Min Act: -0.1700
Data Index: 3842077 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.9811. Min Act: -0.1700
Data Index: 7351963 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.9498. Min Act: -0.1700
Data Index: 1831178 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.9498. Min Act: -0.1700
Data Index: 3718405 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.9498. Min Act: -0.1700
Data Index: 6511203 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.9498. Min Act: -0.1700
Data Index: 7578693 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.9186. Min Act: -0.1699
Data Index: 1606717 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.8873. Min Act: -0.1700
Data Index: 866989 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.8873. Min Act: -0.1700
Data Index: 8184625 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.8873. Min Act: -0.1700
Data Index: 6749670 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.8561. Min Act: -0.1700
Data Index: 8140893 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.8248. Min Act: -0.1700
Data Index: 3718404 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.7936. Min Act: -0.1700
Data Index: 4333741 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.7936. Min Act: -0.1700
Data Index: 1363862 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.8248. Min Act: -0.1700
Data Index: 2109881 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.7623. Min Act: -0.1700
Data Index: 3328875 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.7623. Min Act: -0.1700
Data Index: 7892007 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.7623. Min Act: -0.1700
Data Index: 1992236 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19