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

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

Neuron 2720 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.3129. Min Act: -0.0001

Data Index: 1110196 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.2541. Min Act: -0.0001

Data Index: 170136 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.1106. Min Act: -0.0001

Data Index: 628654 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.1599. Min Act: -0.0001

Data Index: 1312167 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.1233. Min Act: -0.0001

Data Index: 215017 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.0387. Min Act: -0.0001

Data Index: 686868 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.1265. Min Act: -0.0001

Data Index: 233564 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.0181. Min Act: -0.0001

Data Index: 946793 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 1.3129. Min Range: -1.3129

Max Act: 0.9794. Min Act: -0.0001

Data Index: 816557 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.0761. Min Act: -0.0001

Data Index: 1298903 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.0086. Min Act: -0.0001

Data Index: 1215585 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 1.3129. Min Range: -1.3129

Max Act: 0.9541. Min Act: -0.0001

Data Index: 633721 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 1.3129. Min Range: -1.3129

Max Act: 0.8848. Min Act: -0.0001

Data Index: 581727 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 1.3129. Min Range: -1.3129

Max Act: 0.9431. Min Act: -0.0001

Data Index: 612464 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 1.3129. Min Range: -1.3129

Max Act: 0.9943. Min Act: -0.0001

Data Index: 1346265 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.0172. Min Act: -0.0001

Data Index: 1330274 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 1.3129. Min Range: -1.3129

Max Act: 0.9536. Min Act: -0.0001

Data Index: 1547020 (Python Code)

Max Activating Token Index: 363

Text #17

Max Range: 1.3129. Min Range: -1.3129

Max Act: 1.0808. Min Act: -0.0001

Data Index: 438023 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 1.3129. Min Range: -1.3129

Max Act: 0.8500. Min Act: -0.0001

Data Index: 613951 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 1.3129. Min Range: -1.3129

Max Act: 0.9371. Min Act: -0.0001

Data Index: 475229 (C4 (Web Text))

Max Activating Token Index: 956