Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1073 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4104. Min Range: -7.4104
Max Act: 7.4104. Min Act: -0.1700
Data Index: 1467772 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4104. Min Range: -7.4104
Max Act: 7.1916. Min Act: -0.1700
Data Index: 6249172 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4104. Min Range: -7.4104
Max Act: 7.1604. Min Act: -0.1700
Data Index: 4833418 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4104. Min Range: -7.4104
Max Act: 6.9416. Min Act: -0.1700
Data Index: 3991214 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4104. Min Range: -7.4104
Max Act: 6.8791. Min Act: -0.1700
Data Index: 4140773 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4104. Min Range: -7.4104
Max Act: 6.8791. Min Act: -0.1700
Data Index: 5070589 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4104. Min Range: -7.4104
Max Act: 6.8479. Min Act: -0.1700
Data Index: 3669083 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4104. Min Range: -7.4104
Max Act: 6.8479. Min Act: -0.1700
Data Index: 4133062 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4104. Min Range: -7.4104
Max Act: 6.7854. Min Act: -0.1700
Data Index: 4453799 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4104. Min Range: -7.4104
Max Act: 6.7854. Min Act: -0.1700
Data Index: 7008964 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4104. Min Range: -7.4104
Max Act: 6.7854. Min Act: -0.1700
Data Index: 7180534 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4104. Min Range: -7.4104
Max Act: 6.7854. Min Act: -0.1700
Data Index: 2933522 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4104. Min Range: -7.4104
Max Act: 6.7854. Min Act: -0.1700
Data Index: 1738765 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4104. Min Range: -7.4104
Max Act: 6.7854. Min Act: -0.1700
Data Index: 4215480 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4104. Min Range: -7.4104
Max Act: 6.7541. Min Act: -0.1700
Data Index: 685669 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4104. Min Range: -7.4104
Max Act: 6.7541. Min Act: -0.1700
Data Index: 3141916 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4104. Min Range: -7.4104
Max Act: 6.7229. Min Act: -0.1700
Data Index: 2001267 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4104. Min Range: -7.4104
Max Act: 6.6916. Min Act: -0.1700
Data Index: 6548807 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4104. Min Range: -7.4104
Max Act: 6.7229. Min Act: -0.1700
Data Index: 5315783 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4104. Min Range: -7.4104
Max Act: 6.6916. Min Act: -0.1700
Data Index: 2587358 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19