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

Dataset: The Pile

Neuron 2328 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: 0.7520. Min Range: -0.7520

Max Act: 0.7520. Min Act: -0.0000

Data Index: 159778 (The Pile)

Max Activating Token Index: 992

Text #1

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.4847. Min Act: -0.0000

Data Index: 1195342 (The Pile)

Max Activating Token Index: 181

Text #2

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1320331 (The Pile)

Max Activating Token Index: 520

Text #3

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.5029. Min Act: -0.0000

Data Index: 945892 (The Pile)

Max Activating Token Index: 482

Text #4

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.5053. Min Act: -0.0000

Data Index: 166139 (The Pile)

Max Activating Token Index: 83

Text #5

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.4585. Min Act: -0.0000

Data Index: 1284625 (The Pile)

Max Activating Token Index: 340

Text #6

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.4706. Min Act: -0.0000

Data Index: 1083884 (The Pile)

Max Activating Token Index: 593

Text #7

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.4738. Min Act: -0.0000

Data Index: 390358 (The Pile)

Max Activating Token Index: 181

Text #8

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1963052 (The Pile)

Max Activating Token Index: 847

Text #9

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.4470. Min Act: -0.0000

Data Index: 758215 (The Pile)

Max Activating Token Index: 541

Text #10

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1525295 (The Pile)

Max Activating Token Index: 984

Text #11

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1227305 (The Pile)

Max Activating Token Index: 171

Text #12

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.4264. Min Act: -0.0000

Data Index: 908557 (The Pile)

Max Activating Token Index: 884

Text #13

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1490107 (The Pile)

Max Activating Token Index: 179

Text #14

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.4039. Min Act: -0.0000

Data Index: 1015048 (The Pile)

Max Activating Token Index: 958

Text #15

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.4309. Min Act: -0.0000

Data Index: 580199 (The Pile)

Max Activating Token Index: 722

Text #16

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.3727. Min Act: 0.0001

Data Index: 795706 (The Pile)

Max Activating Token Index: 82

Text #17

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.4077. Min Act: -0.0000

Data Index: 1235078 (The Pile)

Max Activating Token Index: 166

Text #18

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.4044. Min Act: -0.0000

Data Index: 1924684 (The Pile)

Max Activating Token Index: 686

Text #19

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1594776 (The Pile)

Max Activating Token Index: 277