Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2948 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8953. Min Range: -6.8953
Max Act: 6.8953. Min Act: -0.1700
Data Index: 5204411 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8953. Min Range: -6.8953
Max Act: 6.8016. Min Act: -0.1700
Data Index: 2106711 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8953. Min Range: -6.8953
Max Act: 6.8016. Min Act: -0.1700
Data Index: 5816108 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8953. Min Range: -6.8953
Max Act: 6.7703. Min Act: -0.1700
Data Index: 5802114 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8953. Min Range: -6.8953
Max Act: 6.7703. Min Act: -0.1700
Data Index: 8782853 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8953. Min Range: -6.8953
Max Act: 6.8016. Min Act: -0.1700
Data Index: 8268342 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8953. Min Range: -6.8953
Max Act: 6.7703. Min Act: -0.1700
Data Index: 2998430 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8953. Min Range: -6.8953
Max Act: 6.7703. Min Act: -0.1700
Data Index: 7886283 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8953. Min Range: -6.8953
Max Act: 6.7703. Min Act: -0.1700
Data Index: 7139030 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8953. Min Range: -6.8953
Max Act: 6.7078. Min Act: -0.1700
Data Index: 7699964 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8953. Min Range: -6.8953
Max Act: 6.7391. Min Act: -0.1700
Data Index: 4691976 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8953. Min Range: -6.8953
Max Act: 6.7391. Min Act: -0.1700
Data Index: 7258327 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8953. Min Range: -6.8953
Max Act: 6.7703. Min Act: -0.1700
Data Index: 4439635 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8953. Min Range: -6.8953
Max Act: 6.6766. Min Act: -0.1700
Data Index: 6826124 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8953. Min Range: -6.8953
Max Act: 6.6766. Min Act: -0.1700
Data Index: 7195422 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8953. Min Range: -6.8953
Max Act: 6.7078. Min Act: -0.1700
Data Index: 3250553 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8953. Min Range: -6.8953
Max Act: 6.6766. Min Act: -0.1700
Data Index: 7574808 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8953. Min Range: -6.8953
Max Act: 6.7078. Min Act: -0.1700
Data Index: 7541631 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8953. Min Range: -6.8953
Max Act: 6.7078. Min Act: -0.1700
Data Index: 4583975 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8953. Min Range: -6.8953
Max Act: 6.7078. Min Act: -0.1700
Data Index: 4540003 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19