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

Dataset: The Pile

Neuron 153 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: 1.4167. Min Range: -1.4167

Max Act: 1.3375. Min Act: -0.0000

Data Index: 303171 (The Pile)

Max Activating Token Index: 777

Text #1

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.4167. Min Act: -0.0000

Data Index: 840870 (The Pile)

Max Activating Token Index: 441

Text #2

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.3881. Min Act: -0.0000

Data Index: 1936875 (The Pile)

Max Activating Token Index: 929

Text #3

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.3735. Min Act: -0.0000

Data Index: 370126 (The Pile)

Max Activating Token Index: 141

Text #4

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.4053. Min Act: -0.0000

Data Index: 501329 (The Pile)

Max Activating Token Index: 87

Text #5

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.2968. Min Act: -0.0000

Data Index: 1617703 (The Pile)

Max Activating Token Index: 175

Text #6

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.3455. Min Act: -0.0000

Data Index: 1161433 (The Pile)

Max Activating Token Index: 1000

Text #7

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.3513. Min Act: -0.0000

Data Index: 1654099 (The Pile)

Max Activating Token Index: 74

Text #8

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.3618. Min Act: -0.0000

Data Index: 1045370 (The Pile)

Max Activating Token Index: 114

Text #9

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.2288. Min Act: -0.0000

Data Index: 1013216 (The Pile)

Max Activating Token Index: 222

Text #10

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.2242. Min Act: -0.0000

Data Index: 628087 (The Pile)

Max Activating Token Index: 264

Text #11

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.3731. Min Act: -0.0000

Data Index: 1458756 (The Pile)

Max Activating Token Index: 215

Text #12

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.3350. Min Act: -0.0000

Data Index: 254716 (The Pile)

Max Activating Token Index: 518

Text #13

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.2970. Min Act: -0.0000

Data Index: 211703 (The Pile)

Max Activating Token Index: 719

Text #14

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.2885. Min Act: -0.0000

Data Index: 648299 (The Pile)

Max Activating Token Index: 258

Text #15

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.4033. Min Act: -0.0000

Data Index: 1423660 (The Pile)

Max Activating Token Index: 698

Text #16

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.2792. Min Act: -0.0000

Data Index: 1699332 (The Pile)

Max Activating Token Index: 635

Text #17

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.3438. Min Act: -0.0000

Data Index: 185064 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.1471. Min Act: -0.0000

Data Index: 1198342 (The Pile)

Max Activating Token Index: 815

Text #19

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.2232. Min Act: -0.0000

Data Index: 1918657 (The Pile)

Max Activating Token Index: 64