Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6122 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0493. Min Range: -8.0493
Max Act: 8.0493. Min Act: -0.1700
Data Index: 3200754 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0493. Min Range: -8.0493
Max Act: 7.9555. Min Act: -0.1700
Data Index: 7610262 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0493. Min Range: -8.0493
Max Act: 7.7993. Min Act: -0.1700
Data Index: 6253670 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0493. Min Range: -8.0493
Max Act: 7.7368. Min Act: -0.1700
Data Index: 4039404 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0493. Min Range: -8.0493
Max Act: 7.5805. Min Act: -0.1700
Data Index: 552363 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0493. Min Range: -8.0493
Max Act: 7.5805. Min Act: -0.1700
Data Index: 2291158 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0493. Min Range: -8.0493
Max Act: 7.5805. Min Act: -0.1700
Data Index: 4518335 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0493. Min Range: -8.0493
Max Act: 7.4868. Min Act: -0.1700
Data Index: 8401967 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0493. Min Range: -8.0493
Max Act: 7.4868. Min Act: -0.1700
Data Index: 1168228 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0493. Min Range: -8.0493
Max Act: 7.4555. Min Act: -0.1700
Data Index: 6741609 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0493. Min Range: -8.0493
Max Act: 7.4243. Min Act: -0.1700
Data Index: 6909484 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0493. Min Range: -8.0493
Max Act: 7.3930. Min Act: -0.1700
Data Index: 5917823 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0493. Min Range: -8.0493
Max Act: 7.3930. Min Act: -0.1700
Data Index: 2114345 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0493. Min Range: -8.0493
Max Act: 7.3618. Min Act: -0.1700
Data Index: 5887167 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0493. Min Range: -8.0493
Max Act: 7.3305. Min Act: -0.1700
Data Index: 4678063 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0493. Min Range: -8.0493
Max Act: 7.2680. Min Act: -0.1700
Data Index: 757259 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0493. Min Range: -8.0493
Max Act: 7.2993. Min Act: -0.1700
Data Index: 4435533 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0493. Min Range: -8.0493
Max Act: 7.2680. Min Act: -0.1700
Data Index: 7449404 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0493. Min Range: -8.0493
Max Act: 7.2368. Min Act: -0.1700
Data Index: 7034830 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0493. Min Range: -8.0493
Max Act: 7.2680. Min Act: -0.1700
Data Index: 1235972 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19