Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4393 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7187. Min Range: -4.7187
Max Act: 4.7187. Min Act: -0.1700
Data Index: 6829863 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7187. Min Range: -4.7187
Max Act: 4.6249. Min Act: -0.1700
Data Index: 4987456 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7187. Min Range: -4.7187
Max Act: 4.5624. Min Act: -0.1700
Data Index: 2225162 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7187. Min Range: -4.7187
Max Act: 4.4999. Min Act: -0.1700
Data Index: 6878061 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7187. Min Range: -4.7187
Max Act: 4.4999. Min Act: -0.1700
Data Index: 4380022 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7187. Min Range: -4.7187
Max Act: 4.4999. Min Act: -0.1700
Data Index: 4575976 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7187. Min Range: -4.7187
Max Act: 4.4687. Min Act: -0.1700
Data Index: 4660779 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7187. Min Range: -4.7187
Max Act: 4.4374. Min Act: -0.1700
Data Index: 5804211 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7187. Min Range: -4.7187
Max Act: 4.4374. Min Act: -0.1700
Data Index: 1494121 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7187. Min Range: -4.7187
Max Act: 4.4062. Min Act: -0.1700
Data Index: 5260995 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7187. Min Range: -4.7187
Max Act: 4.4062. Min Act: -0.1700
Data Index: 2489158 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7187. Min Range: -4.7187
Max Act: 4.4374. Min Act: -0.1700
Data Index: 4953193 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7187. Min Range: -4.7187
Max Act: 4.4062. Min Act: -0.1700
Data Index: 743847 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7187. Min Range: -4.7187
Max Act: 4.4062. Min Act: -0.1700
Data Index: 8400150 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7187. Min Range: -4.7187
Max Act: 4.3749. Min Act: -0.1700
Data Index: 1702636 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7187. Min Range: -4.7187
Max Act: 4.3437. Min Act: -0.1700
Data Index: 3224850 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7187. Min Range: -4.7187
Max Act: 4.3437. Min Act: -0.1700
Data Index: 2065800 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7187. Min Range: -4.7187
Max Act: 4.2812. Min Act: -0.1700
Data Index: 4712870 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7187. Min Range: -4.7187
Max Act: 4.2812. Min Act: -0.1700
Data Index: 5595724 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7187. Min Range: -4.7187
Max Act: 4.3124. Min Act: -0.1700
Data Index: 5587499 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19