Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 178 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1422. Min Range: -8.1422
Max Act: 8.1422. Min Act: -0.1700
Data Index: 5761141 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1422. Min Range: -8.1422
Max Act: 7.7047. Min Act: -0.1700
Data Index: 7634876 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1422. Min Range: -8.1422
Max Act: 7.4234. Min Act: -0.1700
Data Index: 5398157 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1422. Min Range: -8.1422
Max Act: 7.3922. Min Act: -0.1700
Data Index: 7712833 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1422. Min Range: -8.1422
Max Act: 7.3297. Min Act: -0.1700
Data Index: 3645109 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1422. Min Range: -8.1422
Max Act: 7.3297. Min Act: -0.1700
Data Index: 7060519 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1422. Min Range: -8.1422
Max Act: 7.2984. Min Act: -0.1700
Data Index: 5043105 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1422. Min Range: -8.1422
Max Act: 7.2672. Min Act: -0.1700
Data Index: 1380218 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1422. Min Range: -8.1422
Max Act: 7.2984. Min Act: -0.1700
Data Index: 2275222 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1422. Min Range: -8.1422
Max Act: 7.1734. Min Act: -0.1700
Data Index: 3294648 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1422. Min Range: -8.1422
Max Act: 7.1422. Min Act: -0.1700
Data Index: 5697782 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1422. Min Range: -8.1422
Max Act: 7.1734. Min Act: -0.1700
Data Index: 3275879 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1422. Min Range: -8.1422
Max Act: 7.1422. Min Act: -0.1700
Data Index: 8291613 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1422. Min Range: -8.1422
Max Act: 7.1109. Min Act: -0.1700
Data Index: 4244714 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1422. Min Range: -8.1422
Max Act: 7.1422. Min Act: -0.1700
Data Index: 7712834 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1422. Min Range: -8.1422
Max Act: 7.1422. Min Act: -0.1700
Data Index: 555743 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1422. Min Range: -8.1422
Max Act: 7.1422. Min Act: -0.1700
Data Index: 7848696 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1422. Min Range: -8.1422
Max Act: 7.1109. Min Act: -0.1700
Data Index: 6234164 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1422. Min Range: -8.1422
Max Act: 7.0484. Min Act: -0.1700
Data Index: 1587382 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1422. Min Range: -8.1422
Max Act: 7.0484. Min Act: -0.1700
Data Index: 5425541 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19