Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 615 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3170. Min Range: -7.3170
Max Act: 7.3170. Min Act: -0.1700
Data Index: 1269025 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3170. Min Range: -7.3170
Max Act: 6.5982. Min Act: -0.1700
Data Index: 1979942 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3170. Min Range: -7.3170
Max Act: 6.5670. Min Act: -0.1700
Data Index: 292176 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3170. Min Range: -7.3170
Max Act: 6.5670. Min Act: -0.1700
Data Index: 1589620 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3170. Min Range: -7.3170
Max Act: 6.5045. Min Act: -0.1700
Data Index: 2755480 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3170. Min Range: -7.3170
Max Act: 6.5045. Min Act: -0.1700
Data Index: 4571847 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3170. Min Range: -7.3170
Max Act: 6.5045. Min Act: -0.1700
Data Index: 4496179 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3170. Min Range: -7.3170
Max Act: 6.4732. Min Act: -0.1700
Data Index: 5492855 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3170. Min Range: -7.3170
Max Act: 6.4732. Min Act: -0.1700
Data Index: 5680650 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3170. Min Range: -7.3170
Max Act: 6.4420. Min Act: -0.1700
Data Index: 3454202 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3170. Min Range: -7.3170
Max Act: 6.4420. Min Act: -0.1700
Data Index: 8535096 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3170. Min Range: -7.3170
Max Act: 6.4107. Min Act: -0.1700
Data Index: 7537519 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3170. Min Range: -7.3170
Max Act: 6.4107. Min Act: -0.1700
Data Index: 5435515 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3170. Min Range: -7.3170
Max Act: 6.3482. Min Act: -0.1700
Data Index: 4413697 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3170. Min Range: -7.3170
Max Act: 6.3795. Min Act: -0.1700
Data Index: 1266503 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3170. Min Range: -7.3170
Max Act: 6.3795. Min Act: -0.1700
Data Index: 3128232 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3170. Min Range: -7.3170
Max Act: 6.3795. Min Act: -0.1700
Data Index: 4938938 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3170. Min Range: -7.3170
Max Act: 6.3170. Min Act: -0.1700
Data Index: 3899209 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3170. Min Range: -7.3170
Max Act: 6.3170. Min Act: -0.1700
Data Index: 3656409 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3170. Min Range: -7.3170
Max Act: 6.2857. Min Act: -0.1700
Data Index: 8398234 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19