Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3310 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9924. Min Range: -8.9924
Max Act: 8.9924. Min Act: -0.1700
Data Index: 1388650 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9924. Min Range: -8.9924
Max Act: 8.4299. Min Act: -0.1700
Data Index: 2272229 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9924. Min Range: -8.9924
Max Act: 8.1174. Min Act: -0.1700
Data Index: 4998230 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9924. Min Range: -8.9924
Max Act: 7.9924. Min Act: -0.1700
Data Index: 5995272 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9924. Min Range: -8.9924
Max Act: 7.9924. Min Act: -0.1700
Data Index: 7043169 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9924. Min Range: -8.9924
Max Act: 7.9611. Min Act: -0.1700
Data Index: 1763573 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9924. Min Range: -8.9924
Max Act: 7.9611. Min Act: -0.1700
Data Index: 724702 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9924. Min Range: -8.9924
Max Act: 7.8986. Min Act: -0.1700
Data Index: 1946549 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9924. Min Range: -8.9924
Max Act: 7.8049. Min Act: -0.1700
Data Index: 8261167 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9924. Min Range: -8.9924
Max Act: 7.8049. Min Act: -0.1700
Data Index: 2061161 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9924. Min Range: -8.9924
Max Act: 7.7736. Min Act: -0.1700
Data Index: 7563952 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9924. Min Range: -8.9924
Max Act: 7.7736. Min Act: -0.1700
Data Index: 5098778 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9924. Min Range: -8.9924
Max Act: 7.7736. Min Act: -0.1700
Data Index: 1208436 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9924. Min Range: -8.9924
Max Act: 7.7736. Min Act: -0.1700
Data Index: 260887 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9924. Min Range: -8.9924
Max Act: 7.6799. Min Act: -0.1700
Data Index: 3636635 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9924. Min Range: -8.9924
Max Act: 7.7111. Min Act: -0.1700
Data Index: 6868528 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9924. Min Range: -8.9924
Max Act: 7.6799. Min Act: -0.1700
Data Index: 8798538 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9924. Min Range: -8.9924
Max Act: 7.6486. Min Act: -0.1700
Data Index: 5098779 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9924. Min Range: -8.9924
Max Act: 7.5549. Min Act: -0.1700
Data Index: 771477 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9924. Min Range: -8.9924
Max Act: 7.5549. Min Act: -0.1700
Data Index: 2221728 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19