Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 3046 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.0428. Min Range: -3.0428
Max Act: 3.0428. Min Act: -0.1700
Data Index: 6940161 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.0428. Min Range: -3.0428
Max Act: 3.0172. Min Act: -0.1700
Data Index: 7835050 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.9842. Min Act: -0.1700
Data Index: 2925106 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.9753. Min Act: -0.1700
Data Index: 3658450 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.9490. Min Act: -0.1700
Data Index: 4571293 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.9600. Min Act: -0.1700
Data Index: 2847511 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.9436. Min Act: -0.1700
Data Index: 1759389 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.9427. Min Act: -0.1700
Data Index: 1730653 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.9244. Min Act: -0.1700
Data Index: 6096287 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.9318. Min Act: -0.1700
Data Index: 4176305 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.9227. Min Act: -0.1700
Data Index: 2734059 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.9067. Min Act: -0.1700
Data Index: 8587287 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.9330. Min Act: -0.1700
Data Index: 2396719 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.8935. Min Act: -0.1700
Data Index: 3230343 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.9183. Min Act: -0.1700
Data Index: 228644 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.8910. Min Act: -0.1700
Data Index: 7687627 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.8931. Min Act: -0.1700
Data Index: 6814772 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.8972. Min Act: -0.1700
Data Index: 3116494 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.8761. Min Act: -0.1700
Data Index: 1369900 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.8740. Min Act: -0.1700
Data Index: 1355483 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full textTruncated
Full Text #19