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

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

Neuron 3923 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.4244. Min Act: -0.0001

Data Index: 1151961 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.4145. Min Act: -0.0001

Data Index: 459195 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.4118. Min Act: -0.0001

Data Index: 1082940 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.4117. Min Act: -0.0001

Data Index: 118613 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3959. Min Act: -0.0001

Data Index: 839405 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.4116. Min Act: -0.0001

Data Index: 644990 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3574. Min Act: -0.0001

Data Index: 1077109 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3801. Min Act: -0.0001

Data Index: 374479 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3809. Min Act: -0.0001

Data Index: 805281 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.4245. Min Act: -0.0001

Data Index: 1192134 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.4277. Min Act: -0.0001

Data Index: 192576 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.4009. Min Act: -0.0001

Data Index: 730204 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3834. Min Act: -0.0001

Data Index: 196767 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3733. Min Act: -0.0001

Data Index: 668547 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3801. Min Act: -0.0001

Data Index: 171568 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3915. Min Act: -0.0001

Data Index: 125402 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3655. Min Act: -0.0001

Data Index: 1103343 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3636. Min Act: -0.0001

Data Index: 25897 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3872. Min Act: -0.0001

Data Index: 983693 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3721. Min Act: -0.0001

Data Index: 1221261 (C4 (Web Text))

Max Activating Token Index: 242