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

Dataset: The Pile

Neuron 1688 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: 0.4117. Min Range: -0.4117

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1301119 (The Pile)

Max Activating Token Index: 438

Text #1

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3651. Min Act: -0.0000

Data Index: 1746710 (The Pile)

Max Activating Token Index: 1021

Text #2

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3411. Min Act: -0.0000

Data Index: 232248 (The Pile)

Max Activating Token Index: 861

Text #3

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3594. Min Act: -0.0000

Data Index: 1226241 (The Pile)

Max Activating Token Index: 245

Text #4

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3452. Min Act: -0.0000

Data Index: 1101608 (The Pile)

Max Activating Token Index: 84

Text #5

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3624. Min Act: -0.0000

Data Index: 5443 (The Pile)

Max Activating Token Index: 236

Text #6

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3472. Min Act: -0.0000

Data Index: 1283314 (The Pile)

Max Activating Token Index: 414

Text #7

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3532. Min Act: -0.0000

Data Index: 444448 (The Pile)

Max Activating Token Index: 354

Text #8

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3253. Min Act: -0.0000

Data Index: 949489 (The Pile)

Max Activating Token Index: 715

Text #9

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3246. Min Act: -0.0000

Data Index: 427450 (The Pile)

Max Activating Token Index: 602

Text #10

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3089. Min Act: -0.0000

Data Index: 382223 (The Pile)

Max Activating Token Index: 164

Text #11

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3193. Min Act: -0.0000

Data Index: 228644 (The Pile)

Max Activating Token Index: 659

Text #12

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3258. Min Act: -0.0000

Data Index: 938264 (The Pile)

Max Activating Token Index: 914

Text #13

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3174. Min Act: -0.0000

Data Index: 770443 (The Pile)

Max Activating Token Index: 331

Text #14

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3407. Min Act: -0.0000

Data Index: 1720649 (The Pile)

Max Activating Token Index: 514

Text #15

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3572. Min Act: -0.0000

Data Index: 493379 (The Pile)

Max Activating Token Index: 742

Text #16

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.2959. Min Act: -0.0000

Data Index: 921298 (The Pile)

Max Activating Token Index: 214

Text #17

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1193727 (The Pile)

Max Activating Token Index: 829

Text #18

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.2902. Min Act: -0.0000

Data Index: 1940512 (The Pile)

Max Activating Token Index: 955

Text #19

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3240. Min Act: -0.0000

Data Index: 1977592 (The Pile)

Max Activating Token Index: 567