Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 6 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.4293. Min Act: -0.0001

Data Index: 1395162 (Python Code)

Max Activating Token Index: 14

Text #1

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3899. Min Act: -0.0001

Data Index: 1452474 (Python Code)

Max Activating Token Index: 166

Text #2

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3730. Min Act: -0.0001

Data Index: 1467585 (Python Code)

Max Activating Token Index: 553

Text #3

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3300. Min Act: -0.0001

Data Index: 1226758 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3316. Min Act: -0.0001

Data Index: 1557067 (Python Code)

Max Activating Token Index: 173

Text #5

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3083. Min Act: -0.0001

Data Index: 1639873 (Python Code)

Max Activating Token Index: 281

Text #6

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3326. Min Act: -0.0001

Data Index: 1537154 (Python Code)

Max Activating Token Index: 847

Text #7

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3295. Min Act: -0.0001

Data Index: 1485688 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3366. Min Act: -0.0001

Data Index: 1475031 (Python Code)

Max Activating Token Index: 979

Text #9

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3176. Min Act: -0.0001

Data Index: 1489293 (Python Code)

Max Activating Token Index: 1009

Text #10

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3123. Min Act: -0.0001

Data Index: 1505200 (Python Code)

Max Activating Token Index: 138

Text #11

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3208. Min Act: -0.0001

Data Index: 1648716 (Python Code)

Max Activating Token Index: 93

Text #12

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3215. Min Act: -0.0001

Data Index: 1490695 (Python Code)

Max Activating Token Index: 436

Text #13

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3213. Min Act: -0.0001

Data Index: 1595759 (Python Code)

Max Activating Token Index: 118

Text #14

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3186. Min Act: -0.0001

Data Index: 1401895 (Python Code)

Max Activating Token Index: 964

Text #15

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3090. Min Act: -0.0001

Data Index: 1433293 (Python Code)

Max Activating Token Index: 393

Text #16

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3134. Min Act: -0.0001

Data Index: 1635210 (Python Code)

Max Activating Token Index: 172

Text #17

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3136. Min Act: -0.0001

Data Index: 1507210 (Python Code)

Max Activating Token Index: 935

Text #18

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3131. Min Act: -0.0001

Data Index: 1522232 (Python Code)

Max Activating Token Index: 107

Text #19

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3001. Min Act: -0.0001

Data Index: 887590 (C4 (Web Text))

Max Activating Token Index: 1000