Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2503 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0782. Min Range: -2.0782
Max Act: 2.0782. Min Act: -0.1699
Data Index: 5781864 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0782. Min Range: -2.0782
Max Act: 2.0614. Min Act: -0.1700
Data Index: 7189391 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0782. Min Range: -2.0782
Max Act: 2.0446. Min Act: -0.1697
Data Index: 8651598 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0782. Min Range: -2.0782
Max Act: 2.0446. Min Act: -0.1700
Data Index: 5480557 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0782. Min Range: -2.0782
Max Act: 2.0277. Min Act: -0.1700
Data Index: 456682 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0782. Min Range: -2.0782
Max Act: 2.0277. Min Act: -0.1692
Data Index: 7388834 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0782. Min Range: -2.0782
Max Act: 2.0277. Min Act: -0.1700
Data Index: 5979290 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0782. Min Range: -2.0782
Max Act: 2.0277. Min Act: -0.1700
Data Index: 3079087 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0782. Min Range: -2.0782
Max Act: 2.0277. Min Act: -0.1700
Data Index: 6992371 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0782. Min Range: -2.0782
Max Act: 2.0108. Min Act: -0.1694
Data Index: 2230008 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0782. Min Range: -2.0782
Max Act: 2.0277. Min Act: -0.1700
Data Index: 1505532 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0782. Min Range: -2.0782
Max Act: 2.0277. Min Act: -0.1699
Data Index: 714144 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0782. Min Range: -2.0782
Max Act: 1.9939. Min Act: -0.1700
Data Index: 4474909 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0782. Min Range: -2.0782
Max Act: 1.9939. Min Act: -0.1700
Data Index: 6243727 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0782. Min Range: -2.0782
Max Act: 1.9770. Min Act: -0.1700
Data Index: 7197449 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0782. Min Range: -2.0782
Max Act: 1.9770. Min Act: -0.1700
Data Index: 3801799 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0782. Min Range: -2.0782
Max Act: 1.9601. Min Act: -0.1700
Data Index: 6205412 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0782. Min Range: -2.0782
Max Act: 1.9601. Min Act: -0.1700
Data Index: 177524 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0782. Min Range: -2.0782
Max Act: 1.9939. Min Act: -0.1692
Data Index: 727687 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0782. Min Range: -2.0782
Max Act: 1.9601. Min Act: -0.1697
Data Index: 4678131 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19