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

Dataset: The Pile

Neuron 3097 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1762115 (The Pile)

Max Activating Token Index: 479

Text #1

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2563. Min Act: -0.0000

Data Index: 1792571 (The Pile)

Max Activating Token Index: 876

Text #2

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2671. Min Act: -0.0000

Data Index: 1994083 (The Pile)

Max Activating Token Index: 278

Text #3

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2549. Min Act: -0.0000

Data Index: 300898 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2478. Min Act: -0.0000

Data Index: 521029 (The Pile)

Max Activating Token Index: 213

Text #5

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2550. Min Act: -0.0000

Data Index: 149833 (The Pile)

Max Activating Token Index: 435

Text #6

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2538. Min Act: -0.0000

Data Index: 1997313 (The Pile)

Max Activating Token Index: 221

Text #7

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2183. Min Act: -0.0000

Data Index: 371470 (The Pile)

Max Activating Token Index: 736

Text #8

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2324. Min Act: -0.0000

Data Index: 1482826 (The Pile)

Max Activating Token Index: 862

Text #9

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2268. Min Act: -0.0000

Data Index: 1814501 (The Pile)

Max Activating Token Index: 769

Text #10

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1337093 (The Pile)

Max Activating Token Index: 1019

Text #11

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1651964 (The Pile)

Max Activating Token Index: 144

Text #12

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2283. Min Act: -0.0000

Data Index: 226565 (The Pile)

Max Activating Token Index: 101

Text #13

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1197677 (The Pile)

Max Activating Token Index: 882

Text #14

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2223. Min Act: -0.0000

Data Index: 600644 (The Pile)

Max Activating Token Index: 750

Text #15

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2202. Min Act: -0.0000

Data Index: 924760 (The Pile)

Max Activating Token Index: 342

Text #16

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2225. Min Act: -0.0000

Data Index: 399983 (The Pile)

Max Activating Token Index: 943

Text #17

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2219. Min Act: -0.0000

Data Index: 439359 (The Pile)

Max Activating Token Index: 940

Text #18

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2260. Min Act: -0.0000

Data Index: 249189 (The Pile)

Max Activating Token Index: 188

Text #19

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2110. Min Act: -0.0000

Data Index: 1365233 (The Pile)

Max Activating Token Index: 131