Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5082 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9647. Min Range: -7.9647
Max Act: 7.9647. Min Act: -0.1699
Data Index: 8053783 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9647. Min Range: -7.9647
Max Act: 7.8709. Min Act: -0.1700
Data Index: 4333169 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9647. Min Range: -7.9647
Max Act: 7.7772. Min Act: -0.1700
Data Index: 1938129 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9647. Min Range: -7.9647
Max Act: 7.8084. Min Act: -0.1700
Data Index: 1984045 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9647. Min Range: -7.9647
Max Act: 7.6834. Min Act: -0.1700
Data Index: 8821283 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9647. Min Range: -7.9647
Max Act: 7.6209. Min Act: -0.1700
Data Index: 5273139 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9647. Min Range: -7.9647
Max Act: 7.5897. Min Act: -0.1700
Data Index: 3202514 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9647. Min Range: -7.9647
Max Act: 7.5584. Min Act: -0.1700
Data Index: 600906 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9647. Min Range: -7.9647
Max Act: 7.5272. Min Act: -0.1700
Data Index: 1070995 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9647. Min Range: -7.9647
Max Act: 7.5272. Min Act: -0.1700
Data Index: 5910060 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9647. Min Range: -7.9647
Max Act: 7.4334. Min Act: -0.1700
Data Index: 2183440 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9647. Min Range: -7.9647
Max Act: 7.4334. Min Act: -0.1700
Data Index: 6487807 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9647. Min Range: -7.9647
Max Act: 7.3397. Min Act: -0.1700
Data Index: 6485475 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9647. Min Range: -7.9647
Max Act: 7.3084. Min Act: -0.1700
Data Index: 7600446 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9647. Min Range: -7.9647
Max Act: 7.1834. Min Act: -0.1700
Data Index: 7202395 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9647. Min Range: -7.9647
Max Act: 7.1522. Min Act: -0.1700
Data Index: 4201747 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9647. Min Range: -7.9647
Max Act: 7.1209. Min Act: -0.1700
Data Index: 3202513 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9647. Min Range: -7.9647
Max Act: 7.1209. Min Act: -0.1700
Data Index: 1789663 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9647. Min Range: -7.9647
Max Act: 7.1209. Min Act: -0.1700
Data Index: 6985745 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9647. Min Range: -7.9647
Max Act: 7.1209. Min Act: -0.1700
Data Index: 7232400 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19