Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2785 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5166. Min Range: -8.5166
Max Act: 8.5166. Min Act: -0.1700
Data Index: 8229747 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5166. Min Range: -8.5166
Max Act: 8.3291. Min Act: -0.1700
Data Index: 6055917 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5166. Min Range: -8.5166
Max Act: 8.3291. Min Act: -0.1700
Data Index: 7214872 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5166. Min Range: -8.5166
Max Act: 8.1416. Min Act: -0.1700
Data Index: 1037212 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5166. Min Range: -8.5166
Max Act: 8.0791. Min Act: -0.1700
Data Index: 6079812 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5166. Min Range: -8.5166
Max Act: 8.0791. Min Act: -0.1700
Data Index: 1302911 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5166. Min Range: -8.5166
Max Act: 8.0166. Min Act: -0.1700
Data Index: 1163256 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5166. Min Range: -8.5166
Max Act: 7.9541. Min Act: -0.1700
Data Index: 8281638 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5166. Min Range: -8.5166
Max Act: 7.9541. Min Act: -0.1700
Data Index: 5817119 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5166. Min Range: -8.5166
Max Act: 7.8916. Min Act: -0.1700
Data Index: 2923737 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5166. Min Range: -8.5166
Max Act: 7.8916. Min Act: -0.1700
Data Index: 1906221 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5166. Min Range: -8.5166
Max Act: 7.8916. Min Act: -0.1700
Data Index: 478857 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5166. Min Range: -8.5166
Max Act: 7.8916. Min Act: -0.1700
Data Index: 6380766 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5166. Min Range: -8.5166
Max Act: 7.8916. Min Act: -0.1700
Data Index: 605877 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5166. Min Range: -8.5166
Max Act: 7.8916. Min Act: -0.1700
Data Index: 12057 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5166. Min Range: -8.5166
Max Act: 7.8291. Min Act: -0.1700
Data Index: 1917711 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5166. Min Range: -8.5166
Max Act: 7.8291. Min Act: -0.1700
Data Index: 3782797 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5166. Min Range: -8.5166
Max Act: 7.8916. Min Act: -0.1700
Data Index: 408943 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5166. Min Range: -8.5166
Max Act: 7.7666. Min Act: -0.1700
Data Index: 3591108 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5166. Min Range: -8.5166
Max Act: 7.8291. Min Act: -0.1700
Data Index: 6239997 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19