Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3011 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.3481. Min Act: -0.1700
Data Index: 4354528 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.2544. Min Act: -0.1700
Data Index: 4354523 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0981. Min Act: -0.1700
Data Index: 8432515 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.9419. Min Act: -0.1700
Data Index: 7424761 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.9419. Min Act: -0.1700
Data Index: 3637430 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.9731. Min Act: -0.1700
Data Index: 5244314 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.9106. Min Act: -0.1700
Data Index: 8339187 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.8794. Min Act: -0.1700
Data Index: 7971944 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.8794. Min Act: -0.1700
Data Index: 7346841 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.9106. Min Act: -0.1700
Data Index: 2658308 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.8481. Min Act: -0.1700
Data Index: 207510 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.8481. Min Act: -0.1700
Data Index: 3195279 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.8169. Min Act: -0.1700
Data Index: 6591078 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.8169. Min Act: -0.1700
Data Index: 7233420 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.8169. Min Act: -0.1700
Data Index: 8413356 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.7856. Min Act: -0.1700
Data Index: 2430773 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.8169. Min Act: -0.1700
Data Index: 8347461 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.7856. Min Act: -0.1700
Data Index: 133618 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.8169. Min Act: -0.1700
Data Index: 8582563 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.7544. Min Act: -0.1700
Data Index: 4112918 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19