Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1085 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.2749. Min Range: -3.2749
Max Act: 3.2749. Min Act: -0.1700
Data Index: 5813601 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.2749. Min Range: -3.2749
Max Act: 3.2473. Min Act: -0.1700
Data Index: 6927892 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.2749. Min Range: -3.2749
Max Act: 3.2399. Min Act: -0.1700
Data Index: 8377845 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.2749. Min Range: -3.2749
Max Act: 3.1621. Min Act: -0.1700
Data Index: 1647047 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.2749. Min Range: -3.2749
Max Act: 3.1593. Min Act: -0.1700
Data Index: 1973294 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.2749. Min Range: -3.2749
Max Act: 3.0960. Min Act: -0.1700
Data Index: 3847368 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.2749. Min Range: -3.2749
Max Act: 3.0918. Min Act: -0.1700
Data Index: 6067870 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.2749. Min Range: -3.2749
Max Act: 3.0888. Min Act: -0.1700
Data Index: 8297519 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.2749. Min Range: -3.2749
Max Act: 3.0767. Min Act: -0.1700
Data Index: 353556 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.2749. Min Range: -3.2749
Max Act: 3.0687. Min Act: -0.1700
Data Index: 7627155 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.2749. Min Range: -3.2749
Max Act: 3.0374. Min Act: -0.1700
Data Index: 8598384 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.2749. Min Range: -3.2749
Max Act: 3.0475. Min Act: -0.1700
Data Index: 2940803 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.2749. Min Range: -3.2749
Max Act: 3.0288. Min Act: -0.1700
Data Index: 8284603 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.2749. Min Range: -3.2749
Max Act: 3.0165. Min Act: -0.1700
Data Index: 7222536 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.2749. Min Range: -3.2749
Max Act: 3.0417. Min Act: -0.1700
Data Index: 5164317 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.2749. Min Range: -3.2749
Max Act: 3.0051. Min Act: -0.1700
Data Index: 1973295 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.2749. Min Range: -3.2749
Max Act: 3.0186. Min Act: -0.1700
Data Index: 4770864 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.2749. Min Range: -3.2749
Max Act: 2.9988. Min Act: -0.1700
Data Index: 1651155 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.2749. Min Range: -3.2749
Max Act: 3.0253. Min Act: -0.1700
Data Index: 1593547 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.2749. Min Range: -3.2749
Max Act: 3.0189. Min Act: -0.1700
Data Index: 7666129 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full textTruncated
Full Text #19