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

Dataset: The Pile

Neuron 137 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.4322. Min Act: -0.0000

Data Index: 318010 (The Pile)

Max Activating Token Index: 172

Text #1

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.2429. Min Act: -0.0000

Data Index: 97903 (The Pile)

Max Activating Token Index: 278

Text #2

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.0694. Min Act: -0.0000

Data Index: 510897 (The Pile)

Max Activating Token Index: 807

Text #3

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.1085. Min Act: -0.0000

Data Index: 1857871 (The Pile)

Max Activating Token Index: 558

Text #4

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.1084. Min Act: -0.0000

Data Index: 287292 (The Pile)

Max Activating Token Index: 530

Text #5

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.0810. Min Act: -0.0000

Data Index: 575340 (The Pile)

Max Activating Token Index: 296

Text #6

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.0469. Min Act: -0.0000

Data Index: 27301 (The Pile)

Max Activating Token Index: 116

Text #7

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.0249. Min Act: -0.0000

Data Index: 31014 (The Pile)

Max Activating Token Index: 530

Text #8

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.0198. Min Act: -0.0000

Data Index: 1638523 (The Pile)

Max Activating Token Index: 581

Text #9

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.0179. Min Act: -0.0000

Data Index: 1977518 (The Pile)

Max Activating Token Index: 254

Text #10

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.0153. Min Act: -0.0000

Data Index: 155854 (The Pile)

Max Activating Token Index: 442

Text #11

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.1110. Min Act: -0.0000

Data Index: 520267 (The Pile)

Max Activating Token Index: 535

Text #12

Max Range: 2.4322. Min Range: -2.4322

Max Act: 1.9993. Min Act: -0.0000

Data Index: 1173670 (The Pile)

Max Activating Token Index: 73

Text #13

Max Range: 2.4322. Min Range: -2.4322

Max Act: 1.9829. Min Act: -0.0000

Data Index: 876721 (The Pile)

Max Activating Token Index: 189

Text #14

Max Range: 2.4322. Min Range: -2.4322

Max Act: 1.9229. Min Act: -0.0000

Data Index: 279088 (The Pile)

Max Activating Token Index: 367

Text #15

Max Range: 2.4322. Min Range: -2.4322

Max Act: 1.9763. Min Act: -0.0000

Data Index: 958401 (The Pile)

Max Activating Token Index: 985

Text #16

Max Range: 2.4322. Min Range: -2.4322

Max Act: 1.9069. Min Act: -0.0000

Data Index: 1909138 (The Pile)

Max Activating Token Index: 600

Text #17

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.0096. Min Act: -0.0000

Data Index: 869730 (The Pile)

Max Activating Token Index: 256

Text #18

Max Range: 2.4322. Min Range: -2.4322

Max Act: 1.8969. Min Act: -0.0000

Data Index: 815451 (The Pile)

Max Activating Token Index: 664

Text #19

Max Range: 2.4322. Min Range: -2.4322

Max Act: 1.9973. Min Act: -0.0000

Data Index: 1962576 (The Pile)

Max Activating Token Index: 256