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

Dataset: The Pile

Neuron 793 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6438. Min Range: -1.6438

Max Act: 1.6438. Min Act: -0.0000

Data Index: 1376304 (The Pile)

Max Activating Token Index: 178

Text #1

Max Range: 1.6438. Min Range: -1.6438

Max Act: 1.3883. Min Act: -0.0000

Data Index: 1091319 (The Pile)

Max Activating Token Index: 164

Text #2

Max Range: 1.6438. Min Range: -1.6438

Max Act: 1.4393. Min Act: -0.0000

Data Index: 911610 (The Pile)

Max Activating Token Index: 700

Text #3

Max Range: 1.6438. Min Range: -1.6438

Max Act: 1.3491. Min Act: -0.0000

Data Index: 1355933 (The Pile)

Max Activating Token Index: 484

Text #4

Max Range: 1.6438. Min Range: -1.6438

Max Act: 1.2575. Min Act: -0.0000

Data Index: 1646905 (The Pile)

Max Activating Token Index: 201

Text #5

Max Range: 1.6438. Min Range: -1.6438

Max Act: 1.0879. Min Act: -0.0000

Data Index: 1214819 (The Pile)

Max Activating Token Index: 738

Text #6

Max Range: 1.6438. Min Range: -1.6438

Max Act: 1.1221. Min Act: -0.0000

Data Index: 1793416 (The Pile)

Max Activating Token Index: 132

Text #7

Max Range: 1.6438. Min Range: -1.6438

Max Act: 1.0250. Min Act: -0.0000

Data Index: 1911693 (The Pile)

Max Activating Token Index: 939

Text #8

Max Range: 1.6438. Min Range: -1.6438

Max Act: 1.1065. Min Act: -0.0000

Data Index: 609948 (The Pile)

Max Activating Token Index: 73

Text #9

Max Range: 1.6438. Min Range: -1.6438

Max Act: 1.0061. Min Act: -0.0000

Data Index: 427783 (The Pile)

Max Activating Token Index: 309

Text #10

Max Range: 1.6438. Min Range: -1.6438

Max Act: 0.9530. Min Act: -0.0000

Data Index: 137569 (The Pile)

Max Activating Token Index: 165

Text #11

Max Range: 1.6438. Min Range: -1.6438

Max Act: 1.0168. Min Act: -0.0000

Data Index: 970716 (The Pile)

Max Activating Token Index: 735

Text #12

Max Range: 1.6438. Min Range: -1.6438

Max Act: 1.0645. Min Act: -0.0000

Data Index: 457671 (The Pile)

Max Activating Token Index: 703

Text #13

Max Range: 1.6438. Min Range: -1.6438

Max Act: 1.0014. Min Act: -0.0000

Data Index: 572119 (The Pile)

Max Activating Token Index: 451

Text #14

Max Range: 1.6438. Min Range: -1.6438

Max Act: 1.0235. Min Act: -0.0000

Data Index: 93814 (The Pile)

Max Activating Token Index: 381

Text #15

Max Range: 1.6438. Min Range: -1.6438

Max Act: 1.0540. Min Act: -0.0000

Data Index: 874042 (The Pile)

Max Activating Token Index: 407

Text #16

Max Range: 1.6438. Min Range: -1.6438

Max Act: 0.9540. Min Act: -0.0000

Data Index: 1750406 (The Pile)

Max Activating Token Index: 20

Text #17

Max Range: 1.6438. Min Range: -1.6438

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1218000 (The Pile)

Max Activating Token Index: 583

Text #18

Max Range: 1.6438. Min Range: -1.6438

Max Act: 0.9869. Min Act: -0.0000

Data Index: 515666 (The Pile)

Max Activating Token Index: 313

Text #19

Max Range: 1.6438. Min Range: -1.6438

Max Act: 0.9976. Min Act: -0.0000

Data Index: 1816058 (The Pile)

Max Activating Token Index: 230