Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3876 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.1544. Min Range: -0.1544
Max Act: 0.1544. Min Act: -0.0002
Data Index: 906122 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 0.1544. Min Range: -0.1544
Max Act: 0.1380. Min Act: -0.0002
Data Index: 1209325 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 0.1544. Min Range: -0.1544
Max Act: 0.1329. Min Act: -0.0002
Data Index: 571383 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 0.1544. Min Range: -0.1544
Max Act: 0.1363. Min Act: -0.0002
Data Index: 1309609 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 0.1544. Min Range: -0.1544
Max Act: 0.1351. Min Act: -0.0002
Data Index: 468514 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 0.1544. Min Range: -0.1544
Max Act: 0.1239. Min Act: -0.0002
Data Index: 2422 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 0.1544. Min Range: -0.1544
Max Act: 0.1231. Min Act: -0.0002
Data Index: 875364 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 0.1544. Min Range: -0.1544
Max Act: 0.1214. Min Act: -0.0002
Data Index: 286923 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 0.1544. Min Range: -0.1544
Max Act: 0.1181. Min Act: -0.0002
Data Index: 732760 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 0.1544. Min Range: -0.1544
Max Act: 0.1204. Min Act: -0.0002
Data Index: 697614 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 0.1544. Min Range: -0.1544
Max Act: 0.1202. Min Act: -0.0002
Data Index: 911338 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 0.1544. Min Range: -0.1544
Max Act: 0.1186. Min Act: -0.0002
Data Index: 1078277 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 0.1544. Min Range: -0.1544
Max Act: 0.1187. Min Act: -0.0002
Data Index: 1152177 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 0.1544. Min Range: -0.1544
Max Act: 0.1138. Min Act: -0.0002
Data Index: 1264884 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 0.1544. Min Range: -0.1544
Max Act: 0.1121. Min Act: -0.0002
Data Index: 605865 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 0.1544. Min Range: -0.1544
Max Act: 0.1178. Min Act: -0.0002
Data Index: 1345176 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 0.1544. Min Range: -0.1544
Max Act: 0.1096. Min Act: -0.0002
Data Index: 77264 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 0.1544. Min Range: -0.1544
Max Act: 0.1127. Min Act: -0.0002
Data Index: 851569 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 0.1544. Min Range: -0.1544
Max Act: 0.1129. Min Act: -0.0002
Data Index: 6709 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 0.1544. Min Range: -0.1544
Max Act: 0.1119. Min Act: -0.0002
Data Index: 428608 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full textTruncated
Full Text #19