Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2472 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.8863. Min Range: -3.8863
Max Act: 3.8863. Min Act: -0.1700
Data Index: 5513553 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.8863. Min Range: -3.8863
Max Act: 3.8618. Min Act: -0.1700
Data Index: 3831194 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.8863. Min Range: -3.8863
Max Act: 3.8366. Min Act: -0.1700
Data Index: 1900511 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.8863. Min Range: -3.8863
Max Act: 3.7617. Min Act: -0.1700
Data Index: 6926923 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.8863. Min Range: -3.8863
Max Act: 3.7833. Min Act: -0.1700
Data Index: 2179747 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.8863. Min Range: -3.8863
Max Act: 3.7483. Min Act: -0.1700
Data Index: 7377147 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.8863. Min Range: -3.8863
Max Act: 3.7626. Min Act: -0.1700
Data Index: 7483659 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.8863. Min Range: -3.8863
Max Act: 3.7626. Min Act: -0.1700
Data Index: 8740731 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.8863. Min Range: -3.8863
Max Act: 3.7244. Min Act: -0.1700
Data Index: 1133414 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.8863. Min Range: -3.8863
Max Act: 3.7138. Min Act: -0.1700
Data Index: 2581639 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.8863. Min Range: -3.8863
Max Act: 3.7338. Min Act: -0.1700
Data Index: 5111953 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.8863. Min Range: -3.8863
Max Act: 3.7273. Min Act: -0.1700
Data Index: 6063007 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.8863. Min Range: -3.8863
Max Act: 3.6757. Min Act: -0.1700
Data Index: 6108067 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.8863. Min Range: -3.8863
Max Act: 3.7103. Min Act: -0.1700
Data Index: 625321 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.8863. Min Range: -3.8863
Max Act: 3.6617. Min Act: -0.1700
Data Index: 6484439 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.8863. Min Range: -3.8863
Max Act: 3.6642. Min Act: -0.1700
Data Index: 3009300 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.8863. Min Range: -3.8863
Max Act: 3.7075. Min Act: -0.1700
Data Index: 1786313 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.8863. Min Range: -3.8863
Max Act: 3.6483. Min Act: -0.1700
Data Index: 919357 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.8863. Min Range: -3.8863
Max Act: 3.6877. Min Act: -0.1700
Data Index: 1354858 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.8863. Min Range: -3.8863
Max Act: 3.6840. Min Act: -0.1700
Data Index: 5008290 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full textTruncated
Full Text #19