Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 955 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.5164. Min Range: -3.5164
Max Act: 3.5164. Min Act: -0.1700
Data Index: 1170275 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5164. Min Range: -3.5164
Max Act: 3.2340. Min Act: -0.1700
Data Index: 4286022 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5164. Min Range: -3.5164
Max Act: 3.2655. Min Act: -0.1700
Data Index: 35494 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5164. Min Range: -3.5164
Max Act: 3.1869. Min Act: -0.1700
Data Index: 1576479 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5164. Min Range: -3.5164
Max Act: 3.1397. Min Act: -0.1700
Data Index: 2977327 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5164. Min Range: -3.5164
Max Act: 3.1397. Min Act: -0.1700
Data Index: 3593047 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5164. Min Range: -3.5164
Max Act: 3.1239. Min Act: -0.1700
Data Index: 6808431 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5164. Min Range: -3.5164
Max Act: 3.1239. Min Act: -0.1700
Data Index: 1211951 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5164. Min Range: -3.5164
Max Act: 3.1397. Min Act: -0.1700
Data Index: 5883812 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5164. Min Range: -3.5164
Max Act: 3.1397. Min Act: -0.1700
Data Index: 4610686 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5164. Min Range: -3.5164
Max Act: 3.1239. Min Act: -0.1700
Data Index: 425553 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5164. Min Range: -3.5164
Max Act: 3.1397. Min Act: -0.1700
Data Index: 8629110 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5164. Min Range: -3.5164
Max Act: 3.1239. Min Act: -0.1700
Data Index: 7931164 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5164. Min Range: -3.5164
Max Act: 3.1239. Min Act: -0.1700
Data Index: 1912316 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5164. Min Range: -3.5164
Max Act: 3.1397. Min Act: -0.1700
Data Index: 4186980 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5164. Min Range: -3.5164
Max Act: 3.1081. Min Act: -0.1700
Data Index: 5817058 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5164. Min Range: -3.5164
Max Act: 3.1239. Min Act: -0.1700
Data Index: 1012119 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5164. Min Range: -3.5164
Max Act: 3.1239. Min Act: -0.1700
Data Index: 2136283 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5164. Min Range: -3.5164
Max Act: 3.1081. Min Act: -0.1700
Data Index: 3432803 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5164. Min Range: -3.5164
Max Act: 3.1397. Min Act: -0.1700
Data Index: 2716774 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19