Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3275 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8325. Min Range: -6.8325
Max Act: 6.8325. Min Act: -0.1700
Data Index: 4684716 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8325. Min Range: -6.8325
Max Act: 6.7700. Min Act: -0.1700
Data Index: 6264371 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8325. Min Range: -6.8325
Max Act: 6.2700. Min Act: -0.1700
Data Index: 146088 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8325. Min Range: -6.8325
Max Act: 6.2075. Min Act: -0.1700
Data Index: 5217911 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8325. Min Range: -6.8325
Max Act: 6.1137. Min Act: -0.1700
Data Index: 7317835 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8325. Min Range: -6.8325
Max Act: 6.1137. Min Act: -0.1700
Data Index: 2902633 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8325. Min Range: -6.8325
Max Act: 6.0825. Min Act: -0.1700
Data Index: 6996500 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8325. Min Range: -6.8325
Max Act: 6.0512. Min Act: -0.1700
Data Index: 2554741 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8325. Min Range: -6.8325
Max Act: 5.9887. Min Act: -0.1700
Data Index: 8718453 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8325. Min Range: -6.8325
Max Act: 5.9887. Min Act: -0.1700
Data Index: 4154071 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8325. Min Range: -6.8325
Max Act: 5.9575. Min Act: -0.1700
Data Index: 4579631 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8325. Min Range: -6.8325
Max Act: 5.9575. Min Act: -0.1700
Data Index: 678199 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8325. Min Range: -6.8325
Max Act: 5.9262. Min Act: -0.1700
Data Index: 4467311 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8325. Min Range: -6.8325
Max Act: 5.9262. Min Act: -0.1700
Data Index: 8519700 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8325. Min Range: -6.8325
Max Act: 5.9575. Min Act: -0.1700
Data Index: 8213974 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8325. Min Range: -6.8325
Max Act: 5.8950. Min Act: -0.1700
Data Index: 1124180 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8325. Min Range: -6.8325
Max Act: 5.8325. Min Act: -0.1700
Data Index: 3202527 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8325. Min Range: -6.8325
Max Act: 5.8325. Min Act: -0.1700
Data Index: 3194381 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8325. Min Range: -6.8325
Max Act: 5.8325. Min Act: -0.1700
Data Index: 2666594 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8325. Min Range: -6.8325
Max Act: 5.8637. Min Act: -0.1700
Data Index: 5894031 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19