Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1023 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2808. Min Range: -3.2808
Max Act: 3.2808. Min Act: -0.1700
Data Index: 1589653 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2808. Min Range: -3.2808
Max Act: 3.2180. Min Act: -0.1700
Data Index: 3145084 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2808. Min Range: -3.2808
Max Act: 3.1865. Min Act: -0.1700
Data Index: 1388435 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2808. Min Range: -3.2808
Max Act: 3.1708. Min Act: -0.1700
Data Index: 3021162 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2808. Min Range: -3.2808
Max Act: 3.1393. Min Act: -0.1700
Data Index: 4575901 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2808. Min Range: -3.2808
Max Act: 3.1236. Min Act: -0.1700
Data Index: 5477558 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2808. Min Range: -3.2808
Max Act: 3.1236. Min Act: -0.1700
Data Index: 4380113 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2808. Min Range: -3.2808
Max Act: 3.1236. Min Act: -0.1700
Data Index: 1350280 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2808. Min Range: -3.2808
Max Act: 3.1078. Min Act: -0.1700
Data Index: 5232470 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2808. Min Range: -3.2808
Max Act: 3.0763. Min Act: -0.1700
Data Index: 5431556 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2808. Min Range: -3.2808
Max Act: 3.0447. Min Act: -0.1700
Data Index: 6306685 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2808. Min Range: -3.2808
Max Act: 3.0289. Min Act: -0.1700
Data Index: 1689390 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2808. Min Range: -3.2808
Max Act: 3.0289. Min Act: -0.1700
Data Index: 1046070 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2808. Min Range: -3.2808
Max Act: 3.0289. Min Act: -0.1700
Data Index: 6472985 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2808. Min Range: -3.2808
Max Act: 3.0132. Min Act: -0.1700
Data Index: 7431415 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2808. Min Range: -3.2808
Max Act: 3.0132. Min Act: -0.1700
Data Index: 2083589 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2808. Min Range: -3.2808
Max Act: 2.9815. Min Act: -0.1700
Data Index: 3479683 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2808. Min Range: -3.2808
Max Act: 3.0132. Min Act: -0.1700
Data Index: 7123848 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2808. Min Range: -3.2808
Max Act: 2.9974. Min Act: -0.1700
Data Index: 2034572 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2808. Min Range: -3.2808
Max Act: 2.9815. Min Act: -0.1700
Data Index: 668495 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19