Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3282 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7549. Min Range: -5.7549
Max Act: 5.7549. Min Act: -0.1700
Data Index: 1401785 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7549. Min Range: -5.7549
Max Act: 5.5049. Min Act: -0.1700
Data Index: 8395605 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7549. Min Range: -5.7549
Max Act: 5.4737. Min Act: -0.1700
Data Index: 1926075 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7549. Min Range: -5.7549
Max Act: 5.4424. Min Act: -0.1700
Data Index: 7637587 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7549. Min Range: -5.7549
Max Act: 5.4112. Min Act: -0.1700
Data Index: 8287348 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7549. Min Range: -5.7549
Max Act: 5.4424. Min Act: -0.1700
Data Index: 7767445 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7549. Min Range: -5.7549
Max Act: 5.4112. Min Act: -0.1700
Data Index: 3758528 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7549. Min Range: -5.7549
Max Act: 5.3799. Min Act: -0.1700
Data Index: 8167553 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7549. Min Range: -5.7549
Max Act: 5.3799. Min Act: -0.1700
Data Index: 26469 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7549. Min Range: -5.7549
Max Act: 5.3174. Min Act: -0.1700
Data Index: 593074 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7549. Min Range: -5.7549
Max Act: 5.2549. Min Act: -0.1700
Data Index: 952222 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7549. Min Range: -5.7549
Max Act: 5.3174. Min Act: -0.1700
Data Index: 2788036 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7549. Min Range: -5.7549
Max Act: 5.3174. Min Act: -0.1700
Data Index: 1097709 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7549. Min Range: -5.7549
Max Act: 5.3174. Min Act: -0.1700
Data Index: 137007 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7549. Min Range: -5.7549
Max Act: 5.3174. Min Act: -0.1700
Data Index: 7582283 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7549. Min Range: -5.7549
Max Act: 5.2862. Min Act: -0.1700
Data Index: 7042272 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7549. Min Range: -5.7549
Max Act: 5.2862. Min Act: -0.1700
Data Index: 8480547 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7549. Min Range: -5.7549
Max Act: 5.2862. Min Act: -0.1700
Data Index: 7319293 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7549. Min Range: -5.7549
Max Act: 5.2237. Min Act: -0.1700
Data Index: 1399833 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7549. Min Range: -5.7549
Max Act: 5.2549. Min Act: -0.1700
Data Index: 4778672 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19