Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2830 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5740. Min Range: -4.5740
Max Act: 4.5740. Min Act: -0.1700
Data Index: 2460798 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5740. Min Range: -4.5740
Max Act: 4.3865. Min Act: -0.1700
Data Index: 6417490 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5740. Min Range: -4.5740
Max Act: 4.3552. Min Act: -0.1700
Data Index: 4463904 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5740. Min Range: -4.5740
Max Act: 4.3240. Min Act: -0.1700
Data Index: 2558202 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5740. Min Range: -4.5740
Max Act: 4.2615. Min Act: -0.1700
Data Index: 8281082 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5740. Min Range: -4.5740
Max Act: 4.2302. Min Act: -0.1700
Data Index: 7081393 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5740. Min Range: -4.5740
Max Act: 4.2302. Min Act: -0.1700
Data Index: 5919581 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5740. Min Range: -4.5740
Max Act: 4.2615. Min Act: -0.1700
Data Index: 4904611 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5740. Min Range: -4.5740
Max Act: 4.2302. Min Act: -0.1700
Data Index: 7926625 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5740. Min Range: -4.5740
Max Act: 4.1990. Min Act: -0.1700
Data Index: 5056357 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5740. Min Range: -4.5740
Max Act: 4.1990. Min Act: -0.1700
Data Index: 200301 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5740. Min Range: -4.5740
Max Act: 4.1990. Min Act: -0.1700
Data Index: 1568801 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5740. Min Range: -4.5740
Max Act: 4.1365. Min Act: -0.1700
Data Index: 7081391 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5740. Min Range: -4.5740
Max Act: 4.1677. Min Act: -0.1700
Data Index: 403224 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5740. Min Range: -4.5740
Max Act: 4.1677. Min Act: -0.1700
Data Index: 7772861 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5740. Min Range: -4.5740
Max Act: 4.1365. Min Act: -0.1700
Data Index: 6381572 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5740. Min Range: -4.5740
Max Act: 4.1365. Min Act: -0.1700
Data Index: 5463827 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5740. Min Range: -4.5740
Max Act: 4.1052. Min Act: -0.1700
Data Index: 6381566 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5740. Min Range: -4.5740
Max Act: 4.1052. Min Act: -0.1700
Data Index: 6563964 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5740. Min Range: -4.5740
Max Act: 4.0740. Min Act: -0.1700
Data Index: 2428480 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19