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

Dataset: The Pile

Neuron 3061 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.6469. Min Act: -0.0000

Data Index: 1429374 (The Pile)

Max Activating Token Index: 207

Text #1

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.5075. Min Act: -0.0000

Data Index: 1581390 (The Pile)

Max Activating Token Index: 484

Text #2

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.4042. Min Act: -0.0000

Data Index: 1408402 (The Pile)

Max Activating Token Index: 190

Text #3

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.3278. Min Act: -0.0000

Data Index: 423443 (The Pile)

Max Activating Token Index: 550

Text #4

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.2943. Min Act: -0.0000

Data Index: 1083410 (The Pile)

Max Activating Token Index: 705

Text #5

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.3007. Min Act: -0.0000

Data Index: 656466 (The Pile)

Max Activating Token Index: 486

Text #6

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.3191. Min Act: -0.0000

Data Index: 1620631 (The Pile)

Max Activating Token Index: 315

Text #7

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.3411. Min Act: -0.0000

Data Index: 1797933 (The Pile)

Max Activating Token Index: 372

Text #8

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.2654. Min Act: -0.0000

Data Index: 1129112 (The Pile)

Max Activating Token Index: 681

Text #9

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.2480. Min Act: -0.0000

Data Index: 1765740 (The Pile)

Max Activating Token Index: 281

Text #10

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.2462. Min Act: -0.0000

Data Index: 1330467 (The Pile)

Max Activating Token Index: 103

Text #11

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.2286. Min Act: -0.0000

Data Index: 1294208 (The Pile)

Max Activating Token Index: 149

Text #12

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.3369. Min Act: -0.0000

Data Index: 1439194 (The Pile)

Max Activating Token Index: 116

Text #13

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.2880. Min Act: -0.0000

Data Index: 41020 (The Pile)

Max Activating Token Index: 510

Text #14

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.2046. Min Act: -0.0000

Data Index: 1488835 (The Pile)

Max Activating Token Index: 968

Text #15

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.2192. Min Act: -0.0000

Data Index: 1101919 (The Pile)

Max Activating Token Index: 416

Text #16

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.2299. Min Act: -0.0000

Data Index: 1692466 (The Pile)

Max Activating Token Index: 978

Text #17

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.0833. Min Act: -0.0000

Data Index: 917351 (The Pile)

Max Activating Token Index: 597

Text #18

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.1354. Min Act: -0.0000

Data Index: 1543865 (The Pile)

Max Activating Token Index: 572

Text #19

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.1192. Min Act: -0.0000

Data Index: 1378091 (The Pile)

Max Activating Token Index: 847