Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3648 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.4225. Min Act: -0.0002

Data Index: 659503 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3045. Min Act: -0.0002

Data Index: 568866 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3115. Min Act: -0.0002

Data Index: 1172066 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3002. Min Act: -0.0002

Data Index: 64353 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2842. Min Act: -0.0002

Data Index: 421033 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2596. Min Act: -0.0002

Data Index: 1262022 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2548. Min Act: -0.0002

Data Index: 67463 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2654. Min Act: -0.0002

Data Index: 707366 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2393. Min Act: -0.0002

Data Index: 298126 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2429. Min Act: -0.0002

Data Index: 20415 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2344. Min Act: -0.0002

Data Index: 1115524 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2452. Min Act: -0.0002

Data Index: 971335 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2485. Min Act: -0.0002

Data Index: 366916 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2537. Min Act: -0.0002

Data Index: 1061654 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2402. Min Act: -0.0002

Data Index: 464864 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2152. Min Act: -0.0002

Data Index: 1272599 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2037. Min Act: -0.0002

Data Index: 435022 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2284. Min Act: -0.0002

Data Index: 356642 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2101. Min Act: -0.0002

Data Index: 1114696 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2118. Min Act: -0.0002

Data Index: 695579 (C4 (Web Text))

Max Activating Token Index: 358