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

Dataset: The Pile

Neuron 2398 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5314. Min Range: -3.5314

Max Act: 3.4469. Min Act: -0.0000

Data Index: 1332240 (The Pile)

Max Activating Token Index: 141

Text #1

Max Range: 3.5314. Min Range: -3.5314

Max Act: 3.5314. Min Act: -0.0000

Data Index: 618207 (The Pile)

Max Activating Token Index: 234

Text #2

Max Range: 3.5314. Min Range: -3.5314

Max Act: 3.1372. Min Act: -0.0000

Data Index: 1995278 (The Pile)

Max Activating Token Index: 248

Text #3

Max Range: 3.5314. Min Range: -3.5314

Max Act: 3.2390. Min Act: -0.0000

Data Index: 1449451 (The Pile)

Max Activating Token Index: 86

Text #4

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.7708. Min Act: -0.0000

Data Index: 1393118 (The Pile)

Max Activating Token Index: 133

Text #5

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.7940. Min Act: 0.0000

Data Index: 245110 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.6195. Min Act: -0.0000

Data Index: 439070 (The Pile)

Max Activating Token Index: 683

Text #7

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.4570. Min Act: -0.0000

Data Index: 1938414 (The Pile)

Max Activating Token Index: 173

Text #8

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.5697. Min Act: -0.0000

Data Index: 1928426 (The Pile)

Max Activating Token Index: 179

Text #9

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.4259. Min Act: -0.0000

Data Index: 1529104 (The Pile)

Max Activating Token Index: 238

Text #10

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.3525. Min Act: -0.0000

Data Index: 1166161 (The Pile)

Max Activating Token Index: 43

Text #11

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.3170. Min Act: -0.0000

Data Index: 1571383 (The Pile)

Max Activating Token Index: 198

Text #12

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.2737. Min Act: -0.0000

Data Index: 1271101 (The Pile)

Max Activating Token Index: 269

Text #13

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.2513. Min Act: -0.0000

Data Index: 1658232 (The Pile)

Max Activating Token Index: 269

Text #14

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.3739. Min Act: -0.0000

Data Index: 1074494 (The Pile)

Max Activating Token Index: 84

Text #15

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.4816. Min Act: -0.0000

Data Index: 962103 (The Pile)

Max Activating Token Index: 350

Text #16

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.3632. Min Act: -0.0000

Data Index: 466826 (The Pile)

Max Activating Token Index: 578

Text #17

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.2172. Min Act: -0.0000

Data Index: 988614 (The Pile)

Max Activating Token Index: 64

Text #18

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.2782. Min Act: -0.0000

Data Index: 373387 (The Pile)

Max Activating Token Index: 101

Text #19

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.2671. Min Act: -0.0000

Data Index: 122917 (The Pile)

Max Activating Token Index: 111