Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3024 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1067. Min Range: -8.1067
Max Act: 8.1067. Min Act: -0.1700
Data Index: 2653473 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1067. Min Range: -8.1067
Max Act: 7.8255. Min Act: -0.1700
Data Index: 961601 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1067. Min Range: -8.1067
Max Act: 7.7317. Min Act: -0.1700
Data Index: 7240767 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1067. Min Range: -8.1067
Max Act: 7.6067. Min Act: -0.1700
Data Index: 3921802 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1067. Min Range: -8.1067
Max Act: 7.6067. Min Act: -0.1700
Data Index: 308763 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1067. Min Range: -8.1067
Max Act: 7.4192. Min Act: -0.1700
Data Index: 4230433 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1067. Min Range: -8.1067
Max Act: 7.4192. Min Act: -0.1700
Data Index: 1576910 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1067. Min Range: -8.1067
Max Act: 7.4192. Min Act: -0.1700
Data Index: 5783052 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1067. Min Range: -8.1067
Max Act: 7.3880. Min Act: -0.1700
Data Index: 8078508 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1067. Min Range: -8.1067
Max Act: 7.3567. Min Act: -0.1700
Data Index: 5425086 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1067. Min Range: -8.1067
Max Act: 7.3880. Min Act: -0.1700
Data Index: 1824624 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1067. Min Range: -8.1067
Max Act: 7.3255. Min Act: -0.1700
Data Index: 2504218 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1067. Min Range: -8.1067
Max Act: 7.3255. Min Act: -0.1700
Data Index: 2998942 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1067. Min Range: -8.1067
Max Act: 7.2942. Min Act: -0.1700
Data Index: 7837198 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1067. Min Range: -8.1067
Max Act: 7.3255. Min Act: -0.1700
Data Index: 6361088 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1067. Min Range: -8.1067
Max Act: 7.2942. Min Act: -0.1700
Data Index: 4314662 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1067. Min Range: -8.1067
Max Act: 7.2630. Min Act: -0.1700
Data Index: 8338677 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1067. Min Range: -8.1067
Max Act: 7.2317. Min Act: -0.1700
Data Index: 6479711 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1067. Min Range: -8.1067
Max Act: 7.2630. Min Act: -0.1700
Data Index: 7459327 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1067. Min Range: -8.1067
Max Act: 7.2317. Min Act: -0.1700
Data Index: 5379356 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19