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

Dataset: The Pile

Neuron 1374 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7933. Min Act: -0.0000

Data Index: 581844 (The Pile)

Max Activating Token Index: 1010

Text #1

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7356. Min Act: -0.0000

Data Index: 369289 (The Pile)

Max Activating Token Index: 422

Text #2

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7935. Min Act: -0.0000

Data Index: 476923 (The Pile)

Max Activating Token Index: 921

Text #3

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7034. Min Act: -0.0000

Data Index: 1556278 (The Pile)

Max Activating Token Index: 781

Text #4

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.6484. Min Act: -0.0000

Data Index: 1245192 (The Pile)

Max Activating Token Index: 495

Text #5

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.5462. Min Act: -0.0000

Data Index: 311646 (The Pile)

Max Activating Token Index: 288

Text #6

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.5462. Min Act: -0.0000

Data Index: 147948 (The Pile)

Max Activating Token Index: 288

Text #7

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.6094. Min Act: -0.0000

Data Index: 348158 (The Pile)

Max Activating Token Index: 642

Text #8

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.6419. Min Act: -0.0000

Data Index: 332401 (The Pile)

Max Activating Token Index: 969

Text #9

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.5097. Min Act: -0.0000

Data Index: 1522192 (The Pile)

Max Activating Token Index: 949

Text #10

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.5546. Min Act: -0.0000

Data Index: 1980921 (The Pile)

Max Activating Token Index: 436

Text #11

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.3998. Min Act: -0.0000

Data Index: 644266 (The Pile)

Max Activating Token Index: 441

Text #12

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.4515. Min Act: -0.0000

Data Index: 686828 (The Pile)

Max Activating Token Index: 418

Text #13

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.3969. Min Act: -0.0000

Data Index: 915553 (The Pile)

Max Activating Token Index: 823

Text #14

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.4554. Min Act: -0.0000

Data Index: 900233 (The Pile)

Max Activating Token Index: 780

Text #15

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.3499. Min Act: -0.0000

Data Index: 700119 (The Pile)

Max Activating Token Index: 902

Text #16

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.3888. Min Act: -0.0000

Data Index: 927334 (The Pile)

Max Activating Token Index: 458

Text #17

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.3858. Min Act: -0.0000

Data Index: 808106 (The Pile)

Max Activating Token Index: 978

Text #18

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.3045. Min Act: -0.0000

Data Index: 1728231 (The Pile)

Max Activating Token Index: 154

Text #19

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.3444. Min Act: -0.0000

Data Index: 609808 (The Pile)

Max Activating Token Index: 242