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

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

Neuron 328 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9965. Min Range: -3.9965

Max Act: 3.9965. Min Act: -0.0000

Data Index: 760346 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 3.9965. Min Range: -3.9965

Max Act: 3.6168. Min Act: -0.0001

Data Index: 1107792 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 3.9965. Min Range: -3.9965

Max Act: 2.8798. Min Act: -0.0001

Data Index: 775643 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 3.9965. Min Range: -3.9965

Max Act: 3.1658. Min Act: -0.0001

Data Index: 487367 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 3.9965. Min Range: -3.9965

Max Act: 2.5985. Min Act: -0.0001

Data Index: 621383 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 3.9965. Min Range: -3.9965

Max Act: 2.9192. Min Act: -0.0001

Data Index: 547284 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 3.9965. Min Range: -3.9965

Max Act: 2.6177. Min Act: -0.0001

Data Index: 485401 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 3.9965. Min Range: -3.9965

Max Act: 2.8545. Min Act: -0.0001

Data Index: 1018653 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 3.9965. Min Range: -3.9965

Max Act: 2.8403. Min Act: -0.0000

Data Index: 588886 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 3.9965. Min Range: -3.9965

Max Act: 2.4211. Min Act: -0.0001

Data Index: 1084517 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 3.9965. Min Range: -3.9965

Max Act: 2.6926. Min Act: -0.0001

Data Index: 1170931 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 3.9965. Min Range: -3.9965

Max Act: 2.5466. Min Act: -0.0001

Data Index: 1123368 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 3.9965. Min Range: -3.9965

Max Act: 2.2678. Min Act: -0.0000

Data Index: 1114273 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 3.9965. Min Range: -3.9965

Max Act: 2.4540. Min Act: -0.0001

Data Index: 1293821 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 3.9965. Min Range: -3.9965

Max Act: 2.5259. Min Act: -0.0001

Data Index: 1104473 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 3.9965. Min Range: -3.9965

Max Act: 2.6282. Min Act: -0.0001

Data Index: 742295 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 3.9965. Min Range: -3.9965

Max Act: 2.5214. Min Act: -0.0001

Data Index: 449590 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 3.9965. Min Range: -3.9965

Max Act: 2.4266. Min Act: -0.0000

Data Index: 663004 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 3.9965. Min Range: -3.9965

Max Act: 2.2979. Min Act: -0.0000

Data Index: 1055696 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 3.9965. Min Range: -3.9965

Max Act: 2.1321. Min Act: -0.0001

Data Index: 950255 (C4 (Web Text))

Max Activating Token Index: 623