Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 125 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.2092. Min Act: -0.1700
Data Index: 1480225 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.1809. Min Act: -0.1700
Data Index: 3709120 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.1606. Min Act: -0.1700
Data Index: 1547421 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.1696. Min Act: -0.1700
Data Index: 629724 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.1401. Min Act: -0.1700
Data Index: 6465393 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.1363. Min Act: -0.1700
Data Index: 5234237 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.1245. Min Act: -0.1700
Data Index: 2686427 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.1180. Min Act: -0.1700
Data Index: 6710434 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.1102. Min Act: -0.1700
Data Index: 4331879 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.1147. Min Act: -0.1700
Data Index: 5723357 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.0986. Min Act: -0.1700
Data Index: 141098 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.1137. Min Act: -0.1700
Data Index: 4491181 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.0831. Min Act: -0.1700
Data Index: 3437442 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.0987. Min Act: -0.1700
Data Index: 8023065 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.1012. Min Act: -0.1700
Data Index: 6913099 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.1018. Min Act: -0.1700
Data Index: 3231987 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.1017. Min Act: -0.1700
Data Index: 3011322 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.0796. Min Act: -0.1700
Data Index: 2411531 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.0836. Min Act: -0.1700
Data Index: 5105899 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.0811. Min Act: -0.1700
Data Index: 6627887 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full textTruncated
Full Text #19