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

Dataset: The Pile

Neuron 2203 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1401111 (The Pile)

Max Activating Token Index: 48

Text #1

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.5328. Min Act: -0.0000

Data Index: 888075 (The Pile)

Max Activating Token Index: 16

Text #2

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1002896 (The Pile)

Max Activating Token Index: 850

Text #3

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4972. Min Act: -0.0000

Data Index: 254239 (The Pile)

Max Activating Token Index: 64

Text #4

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1461147 (The Pile)

Max Activating Token Index: 602

Text #5

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1952906 (The Pile)

Max Activating Token Index: 10

Text #6

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4597. Min Act: -0.0000

Data Index: 1144365 (The Pile)

Max Activating Token Index: 148

Text #7

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1166319 (The Pile)

Max Activating Token Index: 238

Text #8

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4796. Min Act: -0.0000

Data Index: 129282 (The Pile)

Max Activating Token Index: 212

Text #9

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1645861 (The Pile)

Max Activating Token Index: 459

Text #10

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4642. Min Act: -0.0000

Data Index: 524788 (The Pile)

Max Activating Token Index: 18

Text #11

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4568. Min Act: -0.0000

Data Index: 401302 (The Pile)

Max Activating Token Index: 347

Text #12

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4394. Min Act: -0.0000

Data Index: 159232 (The Pile)

Max Activating Token Index: 847

Text #13

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4313. Min Act: -0.0000

Data Index: 900954 (The Pile)

Max Activating Token Index: 297

Text #14

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4481. Min Act: -0.0000

Data Index: 1182128 (The Pile)

Max Activating Token Index: 417

Text #15

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4277. Min Act: -0.0000

Data Index: 1008327 (The Pile)

Max Activating Token Index: 86

Text #16

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4450. Min Act: -0.0000

Data Index: 583258 (The Pile)

Max Activating Token Index: 427

Text #17

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4151. Min Act: -0.0000

Data Index: 275356 (The Pile)

Max Activating Token Index: 703

Text #18

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4555. Min Act: -0.0000

Data Index: 448935 (The Pile)

Max Activating Token Index: 90

Text #19

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4558. Min Act: -0.0000

Data Index: 1456913 (The Pile)

Max Activating Token Index: 758