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

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

Neuron 2959 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: 1.4337. Min Range: -1.4337

Max Act: 1.4337. Min Act: -0.0001

Data Index: 1149833 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.3427. Min Act: -0.0001

Data Index: 82270 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.3617. Min Act: -0.0001

Data Index: 511083 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.4026. Min Act: -0.0001

Data Index: 81826 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.1263. Min Act: -0.0001

Data Index: 477234 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.2230. Min Act: -0.0001

Data Index: 122550 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.2082. Min Act: -0.0001

Data Index: 958056 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.1542. Min Act: -0.0001

Data Index: 972737 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.1101. Min Act: -0.0001

Data Index: 1323670 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.1347. Min Act: -0.0001

Data Index: 1085721 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.0268. Min Act: -0.0001

Data Index: 1249438 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.0827. Min Act: -0.0001

Data Index: 300574 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.0454. Min Act: -0.0001

Data Index: 353696 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.0450. Min Act: -0.0001

Data Index: 300493 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.0394. Min Act: -0.0001

Data Index: 683286 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.1234. Min Act: -0.0001

Data Index: 628776 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 1.4337. Min Range: -1.4337

Max Act: 0.9023. Min Act: -0.0001

Data Index: 464276 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 1.4337. Min Range: -1.4337

Max Act: 0.9834. Min Act: -0.0001

Data Index: 565088 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 1.4337. Min Range: -1.4337

Max Act: 0.9828. Min Act: -0.0001

Data Index: 189508 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.0360. Min Act: -0.0001

Data Index: 557661 (C4 (Web Text))

Max Activating Token Index: 381