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

Dataset: The Pile

Neuron 1018 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: 1.8301. Min Range: -1.8301

Max Act: 1.8301. Min Act: -0.0000

Data Index: 1654241 (The Pile)

Max Activating Token Index: 647

Text #1

Max Range: 1.8301. Min Range: -1.8301

Max Act: 1.6253. Min Act: -0.0000

Data Index: 1392596 (The Pile)

Max Activating Token Index: 888

Text #2

Max Range: 1.8301. Min Range: -1.8301

Max Act: 1.7585. Min Act: -0.0000

Data Index: 922278 (The Pile)

Max Activating Token Index: 972

Text #3

Max Range: 1.8301. Min Range: -1.8301

Max Act: 1.7419. Min Act: -0.0000

Data Index: 1053610 (The Pile)

Max Activating Token Index: 262

Text #4

Max Range: 1.8301. Min Range: -1.8301

Max Act: 1.6661. Min Act: -0.0000

Data Index: 835763 (The Pile)

Max Activating Token Index: 254

Text #5

Max Range: 1.8301. Min Range: -1.8301

Max Act: 1.5504. Min Act: -0.0000

Data Index: 695153 (The Pile)

Max Activating Token Index: 444

Text #6

Max Range: 1.8301. Min Range: -1.8301

Max Act: 1.3721. Min Act: -0.0000

Data Index: 1657082 (The Pile)

Max Activating Token Index: 10

Text #7

Max Range: 1.8301. Min Range: -1.8301

Max Act: 1.4940. Min Act: -0.0000

Data Index: 1811873 (The Pile)

Max Activating Token Index: 64

Text #8

Max Range: 1.8301. Min Range: -1.8301

Max Act: 1.3261. Min Act: -0.0000

Data Index: 1211259 (The Pile)

Max Activating Token Index: 874

Text #9

Max Range: 1.8301. Min Range: -1.8301

Max Act: 1.3391. Min Act: -0.0000

Data Index: 854915 (The Pile)

Max Activating Token Index: 185

Text #10

Max Range: 1.8301. Min Range: -1.8301

Max Act: 1.4782. Min Act: -0.0000

Data Index: 233455 (The Pile)

Max Activating Token Index: 753

Text #11

Max Range: 1.8301. Min Range: -1.8301

Max Act: 1.3085. Min Act: -0.0000

Data Index: 513859 (The Pile)

Max Activating Token Index: 958

Text #12

Max Range: 1.8301. Min Range: -1.8301

Max Act: 1.3401. Min Act: -0.0000

Data Index: 1666380 (The Pile)

Max Activating Token Index: 760

Text #13

Max Range: 1.8301. Min Range: -1.8301

Max Act: 1.4722. Min Act: -0.0000

Data Index: 466004 (The Pile)

Max Activating Token Index: 259

Text #14

Max Range: 1.8301. Min Range: -1.8301

Max Act: 1.2480. Min Act: -0.0000

Data Index: 1515814 (The Pile)

Max Activating Token Index: 9

Text #15

Max Range: 1.8301. Min Range: -1.8301

Max Act: 1.2841. Min Act: -0.0000

Data Index: 1144700 (The Pile)

Max Activating Token Index: 621

Text #16

Max Range: 1.8301. Min Range: -1.8301

Max Act: 1.1917. Min Act: -0.0000

Data Index: 1291139 (The Pile)

Max Activating Token Index: 73

Text #17

Max Range: 1.8301. Min Range: -1.8301

Max Act: 1.0659. Min Act: -0.0000

Data Index: 1228011 (The Pile)

Max Activating Token Index: 719

Text #18

Max Range: 1.8301. Min Range: -1.8301

Max Act: 1.2292. Min Act: -0.0000

Data Index: 1128061 (The Pile)

Max Activating Token Index: 208

Text #19

Max Range: 1.8301. Min Range: -1.8301

Max Act: 1.1689. Min Act: -0.0000

Data Index: 644342 (The Pile)

Max Activating Token Index: 111