Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 25 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3055. Min Range: -9.3055
Max Act: 9.3055. Min Act: -0.1700
Data Index: 2462302 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3055. Min Range: -9.3055
Max Act: 9.0555. Min Act: -0.1700
Data Index: 6645336 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3055. Min Range: -9.3055
Max Act: 8.8055. Min Act: -0.1700
Data Index: 5486704 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3055. Min Range: -9.3055
Max Act: 8.6805. Min Act: -0.1700
Data Index: 2317549 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3055. Min Range: -9.3055
Max Act: 8.6805. Min Act: -0.1700
Data Index: 6081232 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3055. Min Range: -9.3055
Max Act: 8.6180. Min Act: -0.1700
Data Index: 6553359 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3055. Min Range: -9.3055
Max Act: 8.6180. Min Act: -0.1700
Data Index: 7887668 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3055. Min Range: -9.3055
Max Act: 8.6180. Min Act: -0.1700
Data Index: 1814805 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3055. Min Range: -9.3055
Max Act: 8.6180. Min Act: -0.1700
Data Index: 1331154 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3055. Min Range: -9.3055
Max Act: 8.5555. Min Act: -0.1700
Data Index: 4642432 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3055. Min Range: -9.3055
Max Act: 8.6180. Min Act: -0.1700
Data Index: 7493106 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3055. Min Range: -9.3055
Max Act: 8.4305. Min Act: -0.1700
Data Index: 8383783 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3055. Min Range: -9.3055
Max Act: 8.4305. Min Act: -0.1700
Data Index: 4618300 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3055. Min Range: -9.3055
Max Act: 8.4305. Min Act: -0.1700
Data Index: 6138883 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3055. Min Range: -9.3055
Max Act: 8.3680. Min Act: -0.1700
Data Index: 6835326 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3055. Min Range: -9.3055
Max Act: 8.3680. Min Act: -0.1700
Data Index: 4270533 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3055. Min Range: -9.3055
Max Act: 8.3680. Min Act: -0.1700
Data Index: 7736520 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3055. Min Range: -9.3055
Max Act: 8.3680. Min Act: -0.1700
Data Index: 7789282 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3055. Min Range: -9.3055
Max Act: 8.3680. Min Act: -0.1700
Data Index: 6941557 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3055. Min Range: -9.3055
Max Act: 8.3680. Min Act: -0.1700
Data Index: 3730505 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19