Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1924 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.7652. Min Range: -3.7652
Max Act: 3.7652. Min Act: -0.1700
Data Index: 2070169 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.7652. Min Range: -3.7652
Max Act: 3.6375. Min Act: -0.1700
Data Index: 2732449 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.7652. Min Range: -3.7652
Max Act: 3.6573. Min Act: -0.1700
Data Index: 6024390 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.7652. Min Range: -3.7652
Max Act: 3.6411. Min Act: -0.1700
Data Index: 5570165 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.7652. Min Range: -3.7652
Max Act: 3.5770. Min Act: -0.1700
Data Index: 7129865 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.7652. Min Range: -3.7652
Max Act: 3.5687. Min Act: -0.1700
Data Index: 2934431 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.7652. Min Range: -3.7652
Max Act: 3.5934. Min Act: -0.1700
Data Index: 576950 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.7652. Min Range: -3.7652
Max Act: 3.5641. Min Act: -0.1700
Data Index: 2098664 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.7652. Min Range: -3.7652
Max Act: 3.5919. Min Act: -0.1700
Data Index: 2431848 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.7652. Min Range: -3.7652
Max Act: 3.5973. Min Act: -0.1700
Data Index: 7796074 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.7652. Min Range: -3.7652
Max Act: 3.5428. Min Act: -0.1700
Data Index: 5258392 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.7652. Min Range: -3.7652
Max Act: 3.5417. Min Act: -0.1700
Data Index: 5134562 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.7652. Min Range: -3.7652
Max Act: 3.5274. Min Act: -0.1700
Data Index: 5312241 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.7652. Min Range: -3.7652
Max Act: 3.5129. Min Act: -0.1700
Data Index: 1533781 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.7652. Min Range: -3.7652
Max Act: 3.4967. Min Act: -0.1700
Data Index: 1696217 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.7652. Min Range: -3.7652
Max Act: 3.5181. Min Act: -0.1700
Data Index: 4815442 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.7652. Min Range: -3.7652
Max Act: 3.5199. Min Act: -0.1700
Data Index: 5673695 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.7652. Min Range: -3.7652
Max Act: 3.5409. Min Act: -0.1700
Data Index: 5732086 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.7652. Min Range: -3.7652
Max Act: 3.5070. Min Act: -0.1700
Data Index: 902741 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.7652. Min Range: -3.7652
Max Act: 3.5118. Min Act: -0.1700
Data Index: 3052672 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full textTruncated
Full Text #19