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

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

Neuron 4552 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0188. Min Act: -0.0001

Data Index: 232622 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0002

Data Index: 598415 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0178. Min Act: -0.0001

Data Index: 1084144 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0178. Min Act: -0.0001

Data Index: 620000 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0178. Min Act: -0.0001

Data Index: 783639 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0176. Min Act: -0.0001

Data Index: 1139414 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0179. Min Act: -0.0001

Data Index: 1216202 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0178. Min Act: -0.0001

Data Index: 303574 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0178. Min Act: -0.0001

Data Index: 123835 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0174. Min Act: -0.0001

Data Index: 1220481 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0172. Min Act: -0.0001

Data Index: 144034 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0175. Min Act: -0.0001

Data Index: 1077836 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0169. Min Act: -0.0001

Data Index: 373649 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0168. Min Act: -0.0001

Data Index: 592524 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0167. Min Act: -0.0001

Data Index: 1656319 (Python Code)

Max Activating Token Index: 8

Text #15

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0173. Min Act: -0.0001

Data Index: 217650 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0171. Min Act: -0.0001

Data Index: 1079487 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0169. Min Act: -0.0001

Data Index: 1303115 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0169. Min Act: -0.0001

Data Index: 836082 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0168. Min Act: -0.0001

Data Index: 1137266 (C4 (Web Text))

Max Activating Token Index: 915