Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1218 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0236. Min Act: -0.0006

Data Index: 1288823 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1101947 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1560144 (Python Code)

Max Activating Token Index: 315

Text #3

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0187. Min Act: -0.0006

Data Index: 996627 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0192. Min Act: -0.0006

Data Index: 1374564 (Python Code)

Max Activating Token Index: 414

Text #5

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0181. Min Act: -0.0006

Data Index: 1186842 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0176. Min Act: -0.0006

Data Index: 1319853 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0175. Min Act: -0.0006

Data Index: 233809 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1447808 (Python Code)

Max Activating Token Index: 681

Text #9

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0174. Min Act: -0.0006

Data Index: 402327 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0169. Min Act: -0.0006

Data Index: 1615060 (Python Code)

Max Activating Token Index: 299

Text #11

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0181. Min Act: -0.0005

Data Index: 1574657 (Python Code)

Max Activating Token Index: 557

Text #12

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0165. Min Act: -0.0006

Data Index: 1517141 (Python Code)

Max Activating Token Index: 408

Text #13

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0169. Min Act: -0.0006

Data Index: 1514722 (Python Code)

Max Activating Token Index: 394

Text #14

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0169. Min Act: -0.0006

Data Index: 1586731 (Python Code)

Max Activating Token Index: 735

Text #15

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1462217 (Python Code)

Max Activating Token Index: 97

Text #16

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0159. Min Act: -0.0006

Data Index: 79855 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0162. Min Act: -0.0006

Data Index: 1236931 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0164. Min Act: -0.0006

Data Index: 1046328 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0161. Min Act: -0.0006

Data Index: 365734 (C4 (Web Text))

Max Activating Token Index: 93