Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5202 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4917. Min Range: -8.4917
Max Act: 8.4917. Min Act: -0.1700
Data Index: 8498577 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4917. Min Range: -8.4917
Max Act: 8.1792. Min Act: -0.1700
Data Index: 2198222 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4917. Min Range: -8.4917
Max Act: 8.0854. Min Act: -0.1700
Data Index: 4466373 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4917. Min Range: -8.4917
Max Act: 7.8667. Min Act: -0.1700
Data Index: 6889880 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4917. Min Range: -8.4917
Max Act: 7.7729. Min Act: -0.1700
Data Index: 6101488 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4917. Min Range: -8.4917
Max Act: 7.8042. Min Act: -0.1700
Data Index: 1754169 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4917. Min Range: -8.4917
Max Act: 7.7104. Min Act: -0.1700
Data Index: 5486970 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4917. Min Range: -8.4917
Max Act: 7.7417. Min Act: -0.1700
Data Index: 6674352 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4917. Min Range: -8.4917
Max Act: 7.7417. Min Act: -0.1700
Data Index: 4895712 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4917. Min Range: -8.4917
Max Act: 7.6167. Min Act: -0.1700
Data Index: 4833537 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4917. Min Range: -8.4917
Max Act: 7.5854. Min Act: -0.1700
Data Index: 990080 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4917. Min Range: -8.4917
Max Act: 7.5854. Min Act: -0.1700
Data Index: 8228497 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4917. Min Range: -8.4917
Max Act: 7.5854. Min Act: -0.1700
Data Index: 3164943 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4917. Min Range: -8.4917
Max Act: 7.5542. Min Act: -0.1700
Data Index: 141021 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4917. Min Range: -8.4917
Max Act: 7.5854. Min Act: -0.1700
Data Index: 2925844 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4917. Min Range: -8.4917
Max Act: 7.5854. Min Act: -0.1700
Data Index: 1008053 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4917. Min Range: -8.4917
Max Act: 7.5542. Min Act: -0.1700
Data Index: 3914511 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4917. Min Range: -8.4917
Max Act: 7.5229. Min Act: -0.1700
Data Index: 2334181 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4917. Min Range: -8.4917
Max Act: 7.4917. Min Act: -0.1700
Data Index: 2800595 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4917. Min Range: -8.4917
Max Act: 7.4292. Min Act: -0.1700
Data Index: 5388625 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19