Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7506. Min Range: -8.7506
Max Act: 8.7506. Min Act: -0.1700
Data Index: 4293632 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7506. Min Range: -8.7506
Max Act: 8.7506. Min Act: -0.1700
Data Index: 3468781 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7506. Min Range: -8.7506
Max Act: 8.5631. Min Act: -0.1700
Data Index: 1738445 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7506. Min Range: -8.7506
Max Act: 8.5006. Min Act: -0.1700
Data Index: 7273375 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7506. Min Range: -8.7506
Max Act: 8.3756. Min Act: -0.1700
Data Index: 8093178 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7506. Min Range: -8.7506
Max Act: 8.3756. Min Act: -0.1700
Data Index: 164913 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7506. Min Range: -8.7506
Max Act: 8.3756. Min Act: -0.1700
Data Index: 3910634 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7506. Min Range: -8.7506
Max Act: 8.3131. Min Act: -0.1700
Data Index: 4339947 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7506. Min Range: -8.7506
Max Act: 8.3131. Min Act: -0.1700
Data Index: 934822 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7506. Min Range: -8.7506
Max Act: 8.3131. Min Act: -0.1700
Data Index: 8367704 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7506. Min Range: -8.7506
Max Act: 8.3131. Min Act: -0.1700
Data Index: 1953606 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7506. Min Range: -8.7506
Max Act: 8.3131. Min Act: -0.1700
Data Index: 4293636 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7506. Min Range: -8.7506
Max Act: 8.3131. Min Act: -0.1700
Data Index: 3163748 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7506. Min Range: -8.7506
Max Act: 8.2506. Min Act: -0.1700
Data Index: 5731848 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7506. Min Range: -8.7506
Max Act: 8.3131. Min Act: -0.1700
Data Index: 5787271 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7506. Min Range: -8.7506
Max Act: 8.2506. Min Act: -0.1700
Data Index: 1315043 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7506. Min Range: -8.7506
Max Act: 8.2506. Min Act: -0.1700
Data Index: 4293637 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7506. Min Range: -8.7506
Max Act: 8.2506. Min Act: -0.1700
Data Index: 4744379 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7506. Min Range: -8.7506
Max Act: 8.2506. Min Act: -0.1700
Data Index: 6878321 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7506. Min Range: -8.7506
Max Act: 8.1881. Min Act: -0.1700
Data Index: 6048586 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19