Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 895 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.5255. Min Range: -4.5255
Max Act: 4.5255. Min Act: -0.1700
Data Index: 2688928 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 4.5255. Min Range: -4.5255
Max Act: 4.2142. Min Act: -0.1700
Data Index: 8592290 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 4.5255. Min Range: -4.5255
Max Act: 4.1754. Min Act: -0.1700
Data Index: 7744350 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 4.5255. Min Range: -4.5255
Max Act: 4.1828. Min Act: -0.1700
Data Index: 1477260 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 4.5255. Min Range: -4.5255
Max Act: 4.1316. Min Act: -0.1700
Data Index: 330902 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 4.5255. Min Range: -4.5255
Max Act: 4.1679. Min Act: -0.1700
Data Index: 4242246 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 4.5255. Min Range: -4.5255
Max Act: 4.2044. Min Act: -0.1700
Data Index: 526477 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 4.5255. Min Range: -4.5255
Max Act: 4.1585. Min Act: -0.1700
Data Index: 3727833 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 4.5255. Min Range: -4.5255
Max Act: 4.1106. Min Act: -0.1700
Data Index: 3586306 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 4.5255. Min Range: -4.5255
Max Act: 4.1505. Min Act: -0.1700
Data Index: 5088101 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 4.5255. Min Range: -4.5255
Max Act: 4.0902. Min Act: -0.1700
Data Index: 397420 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 4.5255. Min Range: -4.5255
Max Act: 4.0911. Min Act: -0.1700
Data Index: 3192290 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 4.5255. Min Range: -4.5255
Max Act: 4.1020. Min Act: -0.1700
Data Index: 2805886 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 4.5255. Min Range: -4.5255
Max Act: 4.1123. Min Act: -0.1700
Data Index: 6651457 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 4.5255. Min Range: -4.5255
Max Act: 4.1088. Min Act: -0.1700
Data Index: 4483120 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 4.5255. Min Range: -4.5255
Max Act: 4.0923. Min Act: -0.1700
Data Index: 1393214 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 4.5255. Min Range: -4.5255
Max Act: 4.0984. Min Act: -0.1700
Data Index: 2791821 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 4.5255. Min Range: -4.5255
Max Act: 4.1184. Min Act: -0.1700
Data Index: 8427658 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 4.5255. Min Range: -4.5255
Max Act: 4.0854. Min Act: -0.1700
Data Index: 7163144 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 4.5255. Min Range: -4.5255
Max Act: 4.0674. Min Act: -0.1700
Data Index: 6140617 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full textTruncated
Full Text #19