Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5040 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5027. Min Range: -2.5027

Max Act: 2.5027. Min Act: -0.0000

Data Index: 379707 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 2.5027. Min Range: -2.5027

Max Act: 2.3208. Min Act: -0.0000

Data Index: 413086 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 2.5027. Min Range: -2.5027

Max Act: 2.2182. Min Act: -0.0000

Data Index: 1071583 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 2.5027. Min Range: -2.5027

Max Act: 2.2075. Min Act: -0.0000

Data Index: 1351462 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 2.5027. Min Range: -2.5027

Max Act: 2.1507. Min Act: -0.0000

Data Index: 294181 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 2.5027. Min Range: -2.5027

Max Act: 2.1456. Min Act: -0.0000

Data Index: 162092 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 2.5027. Min Range: -2.5027

Max Act: 2.1299. Min Act: -0.0000

Data Index: 1099232 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 2.5027. Min Range: -2.5027

Max Act: 2.0842. Min Act: 0.0000

Data Index: 1338283 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 2.5027. Min Range: -2.5027

Max Act: 2.0962. Min Act: -0.0000

Data Index: 132547 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 2.5027. Min Range: -2.5027

Max Act: 2.0440. Min Act: -0.0000

Data Index: 487314 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 2.5027. Min Range: -2.5027

Max Act: 2.0515. Min Act: -0.0000

Data Index: 522544 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 2.5027. Min Range: -2.5027

Max Act: 2.0147. Min Act: -0.0000

Data Index: 1310317 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 2.5027. Min Range: -2.5027

Max Act: 1.9263. Min Act: -0.0000

Data Index: 252182 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 2.5027. Min Range: -2.5027

Max Act: 1.8737. Min Act: -0.0000

Data Index: 1328375 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 2.5027. Min Range: -2.5027

Max Act: 1.8691. Min Act: -0.0000

Data Index: 933204 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 2.5027. Min Range: -2.5027

Max Act: 1.7573. Min Act: -0.0000

Data Index: 499523 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 2.5027. Min Range: -2.5027

Max Act: 1.7554. Min Act: -0.0000

Data Index: 1121976 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 2.5027. Min Range: -2.5027

Max Act: 1.8507. Min Act: -0.0000

Data Index: 667451 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 2.5027. Min Range: -2.5027

Max Act: 1.7240. Min Act: -0.0000

Data Index: 1277181 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 2.5027. Min Range: -2.5027

Max Act: 1.7229. Min Act: -0.0000

Data Index: 221995 (C4 (Web Text))

Max Activating Token Index: 299