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

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

Neuron 336 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1683. Min Act: -0.0001

Data Index: 1079015 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1597. Min Act: -0.0001

Data Index: 1515034 (Python Code)

Max Activating Token Index: 156

Text #2

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1417. Min Act: -0.0001

Data Index: 957314 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1369. Min Act: -0.0000

Data Index: 805153 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1302. Min Act: -0.0001

Data Index: 1444126 (Python Code)

Max Activating Token Index: 392

Text #5

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1334. Min Act: -0.0001

Data Index: 173547 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1279. Min Act: -0.0001

Data Index: 1032987 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1228. Min Act: -0.0001

Data Index: 1242411 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1230. Min Act: -0.0001

Data Index: 843873 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1208. Min Act: -0.0001

Data Index: 1143100 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1190. Min Act: -0.0001

Data Index: 207865 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1197. Min Act: -0.0001

Data Index: 314158 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1190. Min Act: 0.0000

Data Index: 555029 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1182. Min Act: -0.0001

Data Index: 994670 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1177. Min Act: -0.0001

Data Index: 62668 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1175. Min Act: -0.0000

Data Index: 1272284 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1166. Min Act: -0.0001

Data Index: 511345 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1160. Min Act: -0.0001

Data Index: 971858 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1190. Min Act: -0.0001

Data Index: 488459 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1403256 (Python Code)

Max Activating Token Index: 162