Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6271 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6487. Min Range: -9.6487
Max Act: 9.6487. Min Act: -0.1700
Data Index: 8473309 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6487. Min Range: -9.6487
Max Act: 9.3987. Min Act: -0.1700
Data Index: 3632187 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6487. Min Range: -9.6487
Max Act: 9.3362. Min Act: -0.1700
Data Index: 5273734 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6487. Min Range: -9.6487
Max Act: 9.1487. Min Act: -0.1700
Data Index: 1911871 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6487. Min Range: -9.6487
Max Act: 9.0862. Min Act: -0.1700
Data Index: 4235217 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6487. Min Range: -9.6487
Max Act: 9.0862. Min Act: -0.1700
Data Index: 801797 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6487. Min Range: -9.6487
Max Act: 9.0862. Min Act: -0.1700
Data Index: 5996278 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6487. Min Range: -9.6487
Max Act: 9.0862. Min Act: -0.1700
Data Index: 49585 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6487. Min Range: -9.6487
Max Act: 9.0237. Min Act: -0.1700
Data Index: 5988029 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6487. Min Range: -9.6487
Max Act: 9.0237. Min Act: -0.1700
Data Index: 2877901 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6487. Min Range: -9.6487
Max Act: 9.0237. Min Act: -0.1700
Data Index: 6168855 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6487. Min Range: -9.6487
Max Act: 9.0237. Min Act: -0.1700
Data Index: 1738018 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6487. Min Range: -9.6487
Max Act: 9.0237. Min Act: -0.1700
Data Index: 1655244 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6487. Min Range: -9.6487
Max Act: 9.0237. Min Act: -0.1700
Data Index: 3487004 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6487. Min Range: -9.6487
Max Act: 8.8987. Min Act: -0.1700
Data Index: 4777106 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6487. Min Range: -9.6487
Max Act: 8.9612. Min Act: -0.1700
Data Index: 5195739 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6487. Min Range: -9.6487
Max Act: 8.8987. Min Act: -0.1700
Data Index: 2538838 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6487. Min Range: -9.6487
Max Act: 8.8987. Min Act: -0.1700
Data Index: 4878404 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6487. Min Range: -9.6487
Max Act: 8.8362. Min Act: -0.1700
Data Index: 1610598 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6487. Min Range: -9.6487
Max Act: 8.8987. Min Act: -0.1700
Data Index: 1465669 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19