Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6114 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5906. Min Range: -9.5906
Max Act: 9.5906. Min Act: -0.1700
Data Index: 1201948 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5906. Min Range: -9.5906
Max Act: 9.4031. Min Act: -0.1700
Data Index: 5412245 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5906. Min Range: -9.5906
Max Act: 9.3406. Min Act: -0.1700
Data Index: 4330584 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5906. Min Range: -9.5906
Max Act: 9.3406. Min Act: -0.1700
Data Index: 4014313 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5906. Min Range: -9.5906
Max Act: 9.2781. Min Act: -0.1700
Data Index: 8381114 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5906. Min Range: -9.5906
Max Act: 9.2781. Min Act: -0.1700
Data Index: 834711 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5906. Min Range: -9.5906
Max Act: 9.1531. Min Act: -0.1700
Data Index: 4330583 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5906. Min Range: -9.5906
Max Act: 9.0906. Min Act: -0.1700
Data Index: 5250218 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5906. Min Range: -9.5906
Max Act: 9.0281. Min Act: -0.1700
Data Index: 4913144 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5906. Min Range: -9.5906
Max Act: 9.0281. Min Act: -0.1700
Data Index: 1201944 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5906. Min Range: -9.5906
Max Act: 8.9656. Min Act: -0.1700
Data Index: 2114287 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5906. Min Range: -9.5906
Max Act: 8.9031. Min Act: -0.1700
Data Index: 2333723 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5906. Min Range: -9.5906
Max Act: 8.8406. Min Act: -0.1700
Data Index: 2704645 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5906. Min Range: -9.5906
Max Act: 8.7781. Min Act: -0.1700
Data Index: 5331874 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5906. Min Range: -9.5906
Max Act: 8.7781. Min Act: -0.1700
Data Index: 6862396 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5906. Min Range: -9.5906
Max Act: 8.7781. Min Act: -0.1700
Data Index: 1201945 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5906. Min Range: -9.5906
Max Act: 8.7156. Min Act: -0.1700
Data Index: 8672155 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5906. Min Range: -9.5906
Max Act: 8.6531. Min Act: -0.1700
Data Index: 67326 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5906. Min Range: -9.5906
Max Act: 8.6531. Min Act: -0.1700
Data Index: 5314424 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5906. Min Range: -9.5906
Max Act: 8.6531. Min Act: -0.1700
Data Index: 3974598 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19