Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 3071 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.5671. Min Range: -3.5671
Max Act: 3.5671. Min Act: -0.1700
Data Index: 5188045 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.5671. Min Range: -3.5671
Max Act: 3.4363. Min Act: -0.1700
Data Index: 4159125 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.5671. Min Range: -3.5671
Max Act: 3.4292. Min Act: -0.1700
Data Index: 1552027 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.5671. Min Range: -3.5671
Max Act: 3.4368. Min Act: -0.1700
Data Index: 6084400 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.5671. Min Range: -3.5671
Max Act: 3.3926. Min Act: -0.1700
Data Index: 6376192 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.5671. Min Range: -3.5671
Max Act: 3.3224. Min Act: -0.1700
Data Index: 23099 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.5671. Min Range: -3.5671
Max Act: 3.3227. Min Act: -0.1700
Data Index: 1618318 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.5671. Min Range: -3.5671
Max Act: 3.3120. Min Act: -0.1700
Data Index: 6917490 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.5671. Min Range: -3.5671
Max Act: 3.2689. Min Act: -0.1700
Data Index: 800597 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.5671. Min Range: -3.5671
Max Act: 3.2831. Min Act: -0.1700
Data Index: 1937906 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.5671. Min Range: -3.5671
Max Act: 3.2754. Min Act: -0.1700
Data Index: 4590304 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.5671. Min Range: -3.5671
Max Act: 3.2425. Min Act: -0.1700
Data Index: 7461718 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.5671. Min Range: -3.5671
Max Act: 3.2577. Min Act: -0.1700
Data Index: 6527309 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.5671. Min Range: -3.5671
Max Act: 3.2678. Min Act: -0.1700
Data Index: 5821839 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.5671. Min Range: -3.5671
Max Act: 3.2624. Min Act: -0.1700
Data Index: 5246615 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.5671. Min Range: -3.5671
Max Act: 3.2321. Min Act: -0.1700
Data Index: 5280462 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.5671. Min Range: -3.5671
Max Act: 3.2296. Min Act: -0.1700
Data Index: 1795950 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.5671. Min Range: -3.5671
Max Act: 3.2264. Min Act: -0.1700
Data Index: 5197287 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.5671. Min Range: -3.5671
Max Act: 3.2371. Min Act: -0.1700
Data Index: 2002331 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.5671. Min Range: -3.5671
Max Act: 3.2066. Min Act: -0.1700
Data Index: 1857573 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full textTruncated
Full Text #19