Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2407 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3554. Min Range: -6.3554
Max Act: 6.3554. Min Act: -0.1700
Data Index: 1661340 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3554. Min Range: -6.3554
Max Act: 6.2616. Min Act: -0.1700
Data Index: 4749540 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3554. Min Range: -6.3554
Max Act: 6.2616. Min Act: -0.1700
Data Index: 2094657 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3554. Min Range: -6.3554
Max Act: 6.2616. Min Act: -0.1700
Data Index: 804980 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3554. Min Range: -6.3554
Max Act: 6.1366. Min Act: -0.1700
Data Index: 1409630 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3554. Min Range: -6.3554
Max Act: 6.1054. Min Act: -0.1700
Data Index: 250311 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3554. Min Range: -6.3554
Max Act: 6.0741. Min Act: -0.1700
Data Index: 4141847 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3554. Min Range: -6.3554
Max Act: 6.0741. Min Act: -0.1700
Data Index: 8238514 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3554. Min Range: -6.3554
Max Act: 5.9804. Min Act: -0.1700
Data Index: 4887543 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3554. Min Range: -6.3554
Max Act: 5.9491. Min Act: -0.1700
Data Index: 5865970 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3554. Min Range: -6.3554
Max Act: 5.9491. Min Act: -0.1700
Data Index: 7151036 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3554. Min Range: -6.3554
Max Act: 5.9491. Min Act: -0.1700
Data Index: 1695679 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3554. Min Range: -6.3554
Max Act: 5.9179. Min Act: -0.1700
Data Index: 1917769 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3554. Min Range: -6.3554
Max Act: 5.8866. Min Act: -0.1700
Data Index: 576444 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3554. Min Range: -6.3554
Max Act: 5.8554. Min Act: -0.1700
Data Index: 5723125 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3554. Min Range: -6.3554
Max Act: 5.8554. Min Act: -0.1700
Data Index: 6668911 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3554. Min Range: -6.3554
Max Act: 5.8241. Min Act: -0.1700
Data Index: 811198 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3554. Min Range: -6.3554
Max Act: 5.8554. Min Act: -0.1700
Data Index: 6461592 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3554. Min Range: -6.3554
Max Act: 5.8554. Min Act: -0.1700
Data Index: 536898 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3554. Min Range: -6.3554
Max Act: 5.8554. Min Act: -0.1700
Data Index: 8219035 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19