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

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

Neuron 2996 in Layer 1

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: 0.2291. Min Range: -0.2291

Max Act: 0.2291. Min Act: -0.0002

Data Index: 858568 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.2291. Min Range: -0.2291

Max Act: 0.1615. Min Act: -0.0002

Data Index: 176992 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.2291. Min Range: -0.2291

Max Act: 0.1471. Min Act: -0.0003

Data Index: 316373 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.2291. Min Range: -0.2291

Max Act: 0.1462. Min Act: -0.0002

Data Index: 1193651 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 0.2291. Min Range: -0.2291

Max Act: 0.1353. Min Act: -0.0002

Data Index: 515218 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 0.2291. Min Range: -0.2291

Max Act: 0.1324. Min Act: -0.0003

Data Index: 1213886 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 0.2291. Min Range: -0.2291

Max Act: 0.1307. Min Act: -0.0002

Data Index: 418056 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 0.2291. Min Range: -0.2291

Max Act: 0.1274. Min Act: -0.0002

Data Index: 1321020 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.2291. Min Range: -0.2291

Max Act: 0.1313. Min Act: -0.0002

Data Index: 244458 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 0.2291. Min Range: -0.2291

Max Act: 0.1272. Min Act: -0.0002

Data Index: 828437 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.2291. Min Range: -0.2291

Max Act: 0.1276. Min Act: -0.0002

Data Index: 374219 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 0.2291. Min Range: -0.2291

Max Act: 0.1289. Min Act: -0.0002

Data Index: 443833 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 0.2291. Min Range: -0.2291

Max Act: 0.1314. Min Act: -0.0002

Data Index: 871795 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.2291. Min Range: -0.2291

Max Act: 0.1257. Min Act: -0.0002

Data Index: 919715 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.2291. Min Range: -0.2291

Max Act: 0.1237. Min Act: -0.0002

Data Index: 968261 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.2291. Min Range: -0.2291

Max Act: 0.1235. Min Act: -0.0002

Data Index: 507663 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.2291. Min Range: -0.2291

Max Act: 0.1206. Min Act: -0.0002

Data Index: 1052552 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 0.2291. Min Range: -0.2291

Max Act: 0.1196. Min Act: -0.0002

Data Index: 397435 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.2291. Min Range: -0.2291

Max Act: 0.1192. Min Act: -0.0002

Data Index: 923266 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.2291. Min Range: -0.2291

Max Act: 0.1168. Min Act: -0.0003

Data Index: 1353506 (C4 (Web Text))

Max Activating Token Index: 187