Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2554 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1191. Min Range: -1.1191

Max Act: 1.1191. Min Act: -0.0000

Data Index: 877850 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 1.1191. Min Range: -1.1191

Max Act: 0.9957. Min Act: -0.0000

Data Index: 652465 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 1.1191. Min Range: -1.1191

Max Act: 0.9503. Min Act: -0.0000

Data Index: 588420 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 1.1191. Min Range: -1.1191

Max Act: 1.0133. Min Act: -0.0000

Data Index: 954531 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 1.1191. Min Range: -1.1191

Max Act: 0.9070. Min Act: -0.0000

Data Index: 249828 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 1.1191. Min Range: -1.1191

Max Act: 0.9138. Min Act: -0.0000

Data Index: 1086729 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 1.1191. Min Range: -1.1191

Max Act: 0.8400. Min Act: -0.0000

Data Index: 119926 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 1.1191. Min Range: -1.1191

Max Act: 0.9104. Min Act: -0.0000

Data Index: 1018305 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 1.1191. Min Range: -1.1191

Max Act: 0.8541. Min Act: -0.0000

Data Index: 87862 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 1.1191. Min Range: -1.1191

Max Act: 0.8509. Min Act: -0.0000

Data Index: 1194090 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 1.1191. Min Range: -1.1191

Max Act: 0.8221. Min Act: -0.0000

Data Index: 200377 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 1.1191. Min Range: -1.1191

Max Act: 0.7954. Min Act: -0.0000

Data Index: 1151460 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 1.1191. Min Range: -1.1191

Max Act: 0.8093. Min Act: -0.0000

Data Index: 53083 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 1.1191. Min Range: -1.1191

Max Act: 0.8083. Min Act: -0.0000

Data Index: 484398 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 1.1191. Min Range: -1.1191

Max Act: 0.7780. Min Act: -0.0000

Data Index: 1163244 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 1.1191. Min Range: -1.1191

Max Act: 0.7988. Min Act: -0.0000

Data Index: 1287140 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 1.1191. Min Range: -1.1191

Max Act: 0.8102. Min Act: -0.0000

Data Index: 550948 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 1.1191. Min Range: -1.1191

Max Act: 0.7372. Min Act: -0.0000

Data Index: 595021 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 1.1191. Min Range: -1.1191

Max Act: 0.8016. Min Act: -0.0000

Data Index: 1128854 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 1.1191. Min Range: -1.1191

Max Act: 0.8227. Min Act: -0.0000

Data Index: 1160058 (C4 (Web Text))

Max Activating Token Index: 267