Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3435 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4329. Min Range: -6.4329
Max Act: 6.4329. Min Act: -0.1700
Data Index: 2172696 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4329. Min Range: -6.4329
Max Act: 6.3391. Min Act: -0.1700
Data Index: 8101866 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4329. Min Range: -6.4329
Max Act: 6.3079. Min Act: -0.1700
Data Index: 5973032 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4329. Min Range: -6.4329
Max Act: 6.3079. Min Act: -0.1700
Data Index: 166116 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4329. Min Range: -6.4329
Max Act: 6.2454. Min Act: -0.1700
Data Index: 2777758 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4329. Min Range: -6.4329
Max Act: 6.2454. Min Act: -0.1700
Data Index: 182069 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4329. Min Range: -6.4329
Max Act: 6.2141. Min Act: -0.1700
Data Index: 2950637 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4329. Min Range: -6.4329
Max Act: 6.2141. Min Act: -0.1700
Data Index: 454977 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4329. Min Range: -6.4329
Max Act: 6.1516. Min Act: -0.1700
Data Index: 2132925 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4329. Min Range: -6.4329
Max Act: 6.2141. Min Act: -0.1700
Data Index: 1056809 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4329. Min Range: -6.4329
Max Act: 6.1516. Min Act: -0.1700
Data Index: 1553770 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4329. Min Range: -6.4329
Max Act: 6.1204. Min Act: -0.1700
Data Index: 8036968 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4329. Min Range: -6.4329
Max Act: 6.1204. Min Act: -0.1700
Data Index: 7852192 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4329. Min Range: -6.4329
Max Act: 6.0891. Min Act: -0.1700
Data Index: 2483034 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4329. Min Range: -6.4329
Max Act: 6.0891. Min Act: -0.1700
Data Index: 34027 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4329. Min Range: -6.4329
Max Act: 6.0579. Min Act: -0.1700
Data Index: 5252392 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4329. Min Range: -6.4329
Max Act: 6.0579. Min Act: -0.1700
Data Index: 2607044 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4329. Min Range: -6.4329
Max Act: 6.0266. Min Act: -0.1700
Data Index: 1089372 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4329. Min Range: -6.4329
Max Act: 6.0266. Min Act: -0.1700
Data Index: 1194911 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4329. Min Range: -6.4329
Max Act: 6.0266. Min Act: -0.1700
Data Index: 1976602 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19