Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4445 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2112. Min Range: -3.2112
Max Act: 3.2112. Min Act: -0.1700
Data Index: 1297850 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2112. Min Range: -3.2112
Max Act: 3.2112. Min Act: -0.1700
Data Index: 6344885 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2112. Min Range: -3.2112
Max Act: 3.2112. Min Act: -0.1700
Data Index: 7392035 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2112. Min Range: -3.2112
Max Act: 3.1797. Min Act: -0.1700
Data Index: 1799711 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2112. Min Range: -3.2112
Max Act: 3.1797. Min Act: -0.1700
Data Index: 5329141 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2112. Min Range: -3.2112
Max Act: 3.1482. Min Act: -0.1700
Data Index: 6690085 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2112. Min Range: -3.2112
Max Act: 3.1482. Min Act: -0.1700
Data Index: 7669528 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2112. Min Range: -3.2112
Max Act: 3.1640. Min Act: -0.1700
Data Index: 757712 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2112. Min Range: -3.2112
Max Act: 3.1482. Min Act: -0.1700
Data Index: 6459457 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2112. Min Range: -3.2112
Max Act: 3.1325. Min Act: -0.1700
Data Index: 2505434 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2112. Min Range: -3.2112
Max Act: 3.1325. Min Act: -0.1700
Data Index: 7534334 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2112. Min Range: -3.2112
Max Act: 3.1325. Min Act: -0.1700
Data Index: 4261362 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2112. Min Range: -3.2112
Max Act: 3.1167. Min Act: -0.1700
Data Index: 2671144 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2112. Min Range: -3.2112
Max Act: 3.1167. Min Act: -0.1700
Data Index: 6299917 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2112. Min Range: -3.2112
Max Act: 3.1010. Min Act: -0.1700
Data Index: 4158373 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2112. Min Range: -3.2112
Max Act: 3.1167. Min Act: -0.1700
Data Index: 817657 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2112. Min Range: -3.2112
Max Act: 3.1010. Min Act: -0.1700
Data Index: 7592995 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2112. Min Range: -3.2112
Max Act: 3.0852. Min Act: -0.1700
Data Index: 1057822 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2112. Min Range: -3.2112
Max Act: 3.0694. Min Act: -0.1700
Data Index: 2120233 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2112. Min Range: -3.2112
Max Act: 3.0852. Min Act: -0.1700
Data Index: 3924690 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19