Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3491 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2585. Min Range: -8.2585
Max Act: 8.2585. Min Act: -0.1700
Data Index: 6248348 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2585. Min Range: -8.2585
Max Act: 8.2272. Min Act: -0.1700
Data Index: 8737500 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2585. Min Range: -8.2585
Max Act: 8.1647. Min Act: -0.1700
Data Index: 2639530 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2585. Min Range: -8.2585
Max Act: 8.1022. Min Act: -0.1700
Data Index: 6070000 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2585. Min Range: -8.2585
Max Act: 8.0710. Min Act: -0.1700
Data Index: 3049654 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2585. Min Range: -8.2585
Max Act: 8.0710. Min Act: -0.1700
Data Index: 6697130 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2585. Min Range: -8.2585
Max Act: 8.0710. Min Act: -0.1700
Data Index: 1561559 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2585. Min Range: -8.2585
Max Act: 8.0397. Min Act: -0.1700
Data Index: 8509873 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2585. Min Range: -8.2585
Max Act: 7.9772. Min Act: -0.1700
Data Index: 656126 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2585. Min Range: -8.2585
Max Act: 7.9772. Min Act: -0.1700
Data Index: 3153155 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2585. Min Range: -8.2585
Max Act: 7.9460. Min Act: -0.1700
Data Index: 6070016 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2585. Min Range: -8.2585
Max Act: 7.9460. Min Act: -0.1700
Data Index: 5792863 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2585. Min Range: -8.2585
Max Act: 7.8835. Min Act: -0.1700
Data Index: 500105 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2585. Min Range: -8.2585
Max Act: 7.8522. Min Act: -0.1700
Data Index: 5566375 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2585. Min Range: -8.2585
Max Act: 7.8522. Min Act: -0.1700
Data Index: 273773 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2585. Min Range: -8.2585
Max Act: 7.7897. Min Act: -0.1700
Data Index: 5695249 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2585. Min Range: -8.2585
Max Act: 7.8210. Min Act: -0.1700
Data Index: 3419185 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2585. Min Range: -8.2585
Max Act: 7.7897. Min Act: -0.1700
Data Index: 6196801 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2585. Min Range: -8.2585
Max Act: 7.7897. Min Act: -0.1700
Data Index: 4448000 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2585. Min Range: -8.2585
Max Act: 7.7585. Min Act: -0.1700
Data Index: 4962121 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19