Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1519 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2046. Min Range: -1.2046

Max Act: 1.2046. Min Act: -0.0000

Data Index: 989831 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.9986. Min Act: -0.0000

Data Index: 1051691 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 1.2046. Min Range: -1.2046

Max Act: 1.0237. Min Act: -0.0000

Data Index: 501036 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8615. Min Act: -0.0000

Data Index: 797394 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8502. Min Act: -0.0000

Data Index: 894876 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8188. Min Act: -0.0000

Data Index: 571927 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8054. Min Act: -0.0000

Data Index: 521384 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8325. Min Act: -0.0000

Data Index: 455986 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7891. Min Act: -0.0000

Data Index: 549035 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7647. Min Act: -0.0000

Data Index: 696648 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7565. Min Act: -0.0000

Data Index: 598033 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7522. Min Act: -0.0000

Data Index: 131385 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8197. Min Act: -0.0000

Data Index: 443110 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7383. Min Act: -0.0000

Data Index: 455338 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7538. Min Act: -0.0000

Data Index: 474712 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7208. Min Act: -0.0000

Data Index: 994047 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7369. Min Act: -0.0000

Data Index: 516409 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1286002 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7530. Min Act: -0.0000

Data Index: 1084264 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7191. Min Act: -0.0000

Data Index: 341012 (C4 (Web Text))

Max Activating Token Index: 840