Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3615 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3598. Min Range: -3.3598
Max Act: 3.3598. Min Act: -0.1700
Data Index: 2014790 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3598. Min Range: -3.3598
Max Act: 3.3284. Min Act: -0.1700
Data Index: 4666765 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3598. Min Range: -3.3598
Max Act: 3.3128. Min Act: -0.1700
Data Index: 8276656 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3598. Min Range: -3.3598
Max Act: 3.3284. Min Act: -0.1700
Data Index: 1352468 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3598. Min Range: -3.3598
Max Act: 3.2814. Min Act: -0.1700
Data Index: 5909373 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3598. Min Range: -3.3598
Max Act: 3.2814. Min Act: -0.1700
Data Index: 2657790 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3598. Min Range: -3.3598
Max Act: 3.2499. Min Act: -0.1700
Data Index: 4391425 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3598. Min Range: -3.3598
Max Act: 3.2342. Min Act: -0.1699
Data Index: 1161006 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3598. Min Range: -3.3598
Max Act: 3.2342. Min Act: -0.1700
Data Index: 390554 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3598. Min Range: -3.3598
Max Act: 3.2185. Min Act: -0.1699
Data Index: 2791767 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3598. Min Range: -3.3598
Max Act: 3.2028. Min Act: -0.1700
Data Index: 8245302 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3598. Min Range: -3.3598
Max Act: 3.1713. Min Act: -0.1700
Data Index: 7567381 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3598. Min Range: -3.3598
Max Act: 3.1871. Min Act: -0.1700
Data Index: 219670 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3598. Min Range: -3.3598
Max Act: 3.1713. Min Act: -0.1700
Data Index: 3975911 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3598. Min Range: -3.3598
Max Act: 3.1713. Min Act: -0.1700
Data Index: 4207113 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3598. Min Range: -3.3598
Max Act: 3.1713. Min Act: -0.1700
Data Index: 7802822 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3598. Min Range: -3.3598
Max Act: 3.1713. Min Act: -0.1700
Data Index: 1787851 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3598. Min Range: -3.3598
Max Act: 3.1713. Min Act: -0.1700
Data Index: 2452748 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3598. Min Range: -3.3598
Max Act: 3.1556. Min Act: -0.1700
Data Index: 5529520 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3598. Min Range: -3.3598
Max Act: 3.1556. Min Act: -0.1700
Data Index: 2608158 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19