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

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

Neuron 3392 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.9266. Min Act: -0.0001

Data Index: 43196 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.7781. Min Act: -0.0001

Data Index: 189187 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.3877. Min Act: -0.0001

Data Index: 238764 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.4259. Min Act: -0.0001

Data Index: 514896 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.3140. Min Act: -0.0001

Data Index: 1110806 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.2817. Min Act: -0.0001

Data Index: 385671 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.1864. Min Act: -0.0001

Data Index: 224952 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.3819. Min Act: -0.0001

Data Index: 611150 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.2427. Min Act: -0.0001

Data Index: 315152 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.3168. Min Act: -0.0001

Data Index: 1174710 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.1957. Min Act: -0.0001

Data Index: 1274107 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.1499. Min Act: -0.0001

Data Index: 437171 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.2235. Min Act: -0.0001

Data Index: 1111624 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.2082. Min Act: -0.0001

Data Index: 1308044 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.2788. Min Act: -0.0001

Data Index: 706160 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.2118. Min Act: -0.0001

Data Index: 695988 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.2108. Min Act: -0.0001

Data Index: 551429 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.1383. Min Act: -0.0001

Data Index: 583843 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.1731. Min Act: -0.0001

Data Index: 593291 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.1712. Min Act: -0.0001

Data Index: 534567 (C4 (Web Text))

Max Activating Token Index: 23