Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2525 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7952. Min Range: -8.7952
Max Act: 8.7952. Min Act: -0.1700
Data Index: 7960502 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7952. Min Range: -8.7952
Max Act: 8.7952. Min Act: -0.1700
Data Index: 861744 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7952. Min Range: -8.7952
Max Act: 8.7327. Min Act: -0.1700
Data Index: 3588228 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7952. Min Range: -8.7952
Max Act: 8.6702. Min Act: -0.1700
Data Index: 7263216 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7952. Min Range: -8.7952
Max Act: 8.6702. Min Act: -0.1700
Data Index: 5059205 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7952. Min Range: -8.7952
Max Act: 8.5765. Min Act: -0.1700
Data Index: 7337507 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7952. Min Range: -8.7952
Max Act: 8.5765. Min Act: -0.1700
Data Index: 2644771 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7952. Min Range: -8.7952
Max Act: 8.5765. Min Act: -0.1700
Data Index: 8159406 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7952. Min Range: -8.7952
Max Act: 8.5140. Min Act: -0.1700
Data Index: 5530567 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7952. Min Range: -8.7952
Max Act: 8.5140. Min Act: -0.1700
Data Index: 881903 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7952. Min Range: -8.7952
Max Act: 8.4202. Min Act: -0.1700
Data Index: 7179061 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7952. Min Range: -8.7952
Max Act: 8.4202. Min Act: -0.1700
Data Index: 60514 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7952. Min Range: -8.7952
Max Act: 8.3890. Min Act: -0.1700
Data Index: 1326099 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7952. Min Range: -8.7952
Max Act: 8.3890. Min Act: -0.1700
Data Index: 5684533 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7952. Min Range: -8.7952
Max Act: 8.3890. Min Act: -0.1700
Data Index: 6877001 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7952. Min Range: -8.7952
Max Act: 8.3890. Min Act: -0.1700
Data Index: 1402068 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7952. Min Range: -8.7952
Max Act: 8.3890. Min Act: -0.1700
Data Index: 4640578 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7952. Min Range: -8.7952
Max Act: 8.3577. Min Act: -0.1700
Data Index: 292861 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7952. Min Range: -8.7952
Max Act: 8.2952. Min Act: -0.1700
Data Index: 6057490 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7952. Min Range: -8.7952
Max Act: 8.2640. Min Act: -0.1700
Data Index: 2018896 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19