Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1432 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1674. Min Act: -0.0002

Data Index: 964297 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1510. Min Act: -0.0001

Data Index: 1260613 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1302. Min Act: -0.0002

Data Index: 366045 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1286. Min Act: -0.0002

Data Index: 804929 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1430. Min Act: -0.0001

Data Index: 1229274 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1398. Min Act: -0.0002

Data Index: 1155229 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1395. Min Act: -0.0001

Data Index: 956623 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1290. Min Act: -0.0002

Data Index: 454644 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1327. Min Act: -0.0001

Data Index: 547680 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1288. Min Act: -0.0001

Data Index: 159577 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1366. Min Act: -0.0002

Data Index: 240751 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1237. Min Act: -0.0001

Data Index: 129810 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1114. Min Act: -0.0001

Data Index: 746076 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1092. Min Act: -0.0002

Data Index: 928199 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1148. Min Act: -0.0002

Data Index: 757196 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1217. Min Act: -0.0002

Data Index: 752091 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1102. Min Act: -0.0001

Data Index: 135320 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1127. Min Act: -0.0001

Data Index: 142189 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1107. Min Act: -0.0002

Data Index: 1162442 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1142. Min Act: -0.0001

Data Index: 295178 (C4 (Web Text))

Max Activating Token Index: 16