Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6054 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2642. Min Range: -9.2642
Max Act: 9.2642. Min Act: -0.1700
Data Index: 5904436 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2642. Min Range: -9.2642
Max Act: 9.0767. Min Act: -0.1700
Data Index: 6310017 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2642. Min Range: -9.2642
Max Act: 9.0767. Min Act: -0.1700
Data Index: 1956530 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2642. Min Range: -9.2642
Max Act: 8.9517. Min Act: -0.1700
Data Index: 4136326 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2642. Min Range: -9.2642
Max Act: 8.8892. Min Act: -0.1700
Data Index: 6381681 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2642. Min Range: -9.2642
Max Act: 8.8267. Min Act: -0.1700
Data Index: 6460656 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2642. Min Range: -9.2642
Max Act: 8.7642. Min Act: -0.1700
Data Index: 8405298 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2642. Min Range: -9.2642
Max Act: 8.7642. Min Act: -0.1700
Data Index: 3172187 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2642. Min Range: -9.2642
Max Act: 8.7017. Min Act: -0.1700
Data Index: 237032 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2642. Min Range: -9.2642
Max Act: 8.6392. Min Act: -0.1700
Data Index: 4474494 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2642. Min Range: -9.2642
Max Act: 8.5767. Min Act: -0.1700
Data Index: 8378381 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2642. Min Range: -9.2642
Max Act: 8.5767. Min Act: -0.1700
Data Index: 3172186 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2642. Min Range: -9.2642
Max Act: 8.6392. Min Act: -0.1700
Data Index: 6520865 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2642. Min Range: -9.2642
Max Act: 8.5767. Min Act: -0.1700
Data Index: 4199988 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2642. Min Range: -9.2642
Max Act: 8.5767. Min Act: -0.1700
Data Index: 2738603 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2642. Min Range: -9.2642
Max Act: 8.5142. Min Act: -0.1700
Data Index: 5577201 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2642. Min Range: -9.2642
Max Act: 8.5142. Min Act: -0.1700
Data Index: 2229165 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2642. Min Range: -9.2642
Max Act: 8.5767. Min Act: -0.1700
Data Index: 8161619 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2642. Min Range: -9.2642
Max Act: 8.4517. Min Act: -0.1700
Data Index: 5874514 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2642. Min Range: -9.2642
Max Act: 8.4517. Min Act: -0.1700
Data Index: 5324180 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19