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

Dataset: The Pile

Neuron 2038 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3123. Min Range: -4.3123

Max Act: 4.0450. Min Act: -0.0000

Data Index: 647524 (The Pile)

Max Activating Token Index: 466

Text #1

Max Range: 4.3123. Min Range: -4.3123

Max Act: 4.3123. Min Act: -0.0000

Data Index: 811066 (The Pile)

Max Activating Token Index: 192

Text #2

Max Range: 4.3123. Min Range: -4.3123

Max Act: 3.9209. Min Act: -0.0000

Data Index: 1713278 (The Pile)

Max Activating Token Index: 294

Text #3

Max Range: 4.3123. Min Range: -4.3123

Max Act: 3.7595. Min Act: -0.0000

Data Index: 367757 (The Pile)

Max Activating Token Index: 202

Text #4

Max Range: 4.3123. Min Range: -4.3123

Max Act: 4.0765. Min Act: -0.0000

Data Index: 1502975 (The Pile)

Max Activating Token Index: 405

Text #5

Max Range: 4.3123. Min Range: -4.3123

Max Act: 3.9895. Min Act: -0.0000

Data Index: 1939381 (The Pile)

Max Activating Token Index: 354

Text #6

Max Range: 4.3123. Min Range: -4.3123

Max Act: 3.7330. Min Act: -0.0000

Data Index: 1789705 (The Pile)

Max Activating Token Index: 328

Text #7

Max Range: 4.3123. Min Range: -4.3123

Max Act: 3.8867. Min Act: -0.0000

Data Index: 1826879 (The Pile)

Max Activating Token Index: 429

Text #8

Max Range: 4.3123. Min Range: -4.3123

Max Act: 3.6369. Min Act: -0.0000

Data Index: 1025528 (The Pile)

Max Activating Token Index: 238

Text #9

Max Range: 4.3123. Min Range: -4.3123

Max Act: 3.5784. Min Act: -0.0000

Data Index: 1254953 (The Pile)

Max Activating Token Index: 333

Text #10

Max Range: 4.3123. Min Range: -4.3123

Max Act: 3.5997. Min Act: -0.0000

Data Index: 789881 (The Pile)

Max Activating Token Index: 403

Text #11

Max Range: 4.3123. Min Range: -4.3123

Max Act: 3.4845. Min Act: -0.0000

Data Index: 398117 (The Pile)

Max Activating Token Index: 562

Text #12

Max Range: 4.3123. Min Range: -4.3123

Max Act: 3.8071. Min Act: -0.0000

Data Index: 1498240 (The Pile)

Max Activating Token Index: 455

Text #13

Max Range: 4.3123. Min Range: -4.3123

Max Act: 3.3046. Min Act: -0.0000

Data Index: 1362129 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 4.3123. Min Range: -4.3123

Max Act: 3.3914. Min Act: -0.0000

Data Index: 650915 (The Pile)

Max Activating Token Index: 809

Text #15

Max Range: 4.3123. Min Range: -4.3123

Max Act: 3.7768. Min Act: -0.0000

Data Index: 887749 (The Pile)

Max Activating Token Index: 799

Text #16

Max Range: 4.3123. Min Range: -4.3123

Max Act: 3.5253. Min Act: -0.0000

Data Index: 815203 (The Pile)

Max Activating Token Index: 285

Text #17

Max Range: 4.3123. Min Range: -4.3123

Max Act: 3.3948. Min Act: -0.0000

Data Index: 479291 (The Pile)

Max Activating Token Index: 729

Text #18

Max Range: 4.3123. Min Range: -4.3123

Max Act: 3.4388. Min Act: -0.0000

Data Index: 271048 (The Pile)

Max Activating Token Index: 601

Text #19

Max Range: 4.3123. Min Range: -4.3123

Max Act: 3.2968. Min Act: -0.0000

Data Index: 1356655 (The Pile)

Max Activating Token Index: 601