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

Dataset: The Pile

Neuron 152 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: 1.9943. Min Range: -1.9943

Max Act: 1.9943. Min Act: -0.0000

Data Index: 731684 (The Pile)

Max Activating Token Index: 538

Text #1

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.4218. Min Act: -0.0000

Data Index: 1549352 (The Pile)

Max Activating Token Index: 958

Text #2

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.4141. Min Act: -0.0000

Data Index: 1219741 (The Pile)

Max Activating Token Index: 1013

Text #3

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.3035. Min Act: -0.0000

Data Index: 957511 (The Pile)

Max Activating Token Index: 198

Text #4

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.2318. Min Act: -0.0000

Data Index: 1346712 (The Pile)

Max Activating Token Index: 855

Text #5

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.2920. Min Act: -0.0000

Data Index: 843780 (The Pile)

Max Activating Token Index: 214

Text #6

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.1812. Min Act: -0.0000

Data Index: 1038459 (The Pile)

Max Activating Token Index: 285

Text #7

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.0583. Min Act: -0.0000

Data Index: 119549 (The Pile)

Max Activating Token Index: 241

Text #8

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.1132. Min Act: -0.0000

Data Index: 304688 (The Pile)

Max Activating Token Index: 143

Text #9

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.0342. Min Act: -0.0000

Data Index: 14618 (The Pile)

Max Activating Token Index: 355

Text #10

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.0889. Min Act: -0.0000

Data Index: 42377 (The Pile)

Max Activating Token Index: 621

Text #11

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.0935. Min Act: -0.0000

Data Index: 1115361 (The Pile)

Max Activating Token Index: 496

Text #12

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.0355. Min Act: -0.0000

Data Index: 933221 (The Pile)

Max Activating Token Index: 124

Text #13

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.0607. Min Act: -0.0000

Data Index: 219599 (The Pile)

Max Activating Token Index: 448

Text #14

Max Range: 1.9943. Min Range: -1.9943

Max Act: 0.9753. Min Act: -0.0000

Data Index: 693136 (The Pile)

Max Activating Token Index: 545

Text #15

Max Range: 1.9943. Min Range: -1.9943

Max Act: 0.9947. Min Act: -0.0000

Data Index: 193029 (The Pile)

Max Activating Token Index: 705

Text #16

Max Range: 1.9943. Min Range: -1.9943

Max Act: 0.9846. Min Act: -0.0000

Data Index: 1209863 (The Pile)

Max Activating Token Index: 895

Text #17

Max Range: 1.9943. Min Range: -1.9943

Max Act: 0.9946. Min Act: -0.0000

Data Index: 1089322 (The Pile)

Max Activating Token Index: 536

Text #18

Max Range: 1.9943. Min Range: -1.9943

Max Act: 0.9883. Min Act: -0.0000

Data Index: 741299 (The Pile)

Max Activating Token Index: 751

Text #19

Max Range: 1.9943. Min Range: -1.9943

Max Act: 0.9826. Min Act: -0.0000

Data Index: 206282 (The Pile)

Max Activating Token Index: 266