Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2598 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0148. Min Range: -1.0148

Max Act: 1.0148. Min Act: -0.0001

Data Index: 616227 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.9474. Min Act: -0.0001

Data Index: 337819 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.8637. Min Act: -0.0001

Data Index: 562459 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.7731. Min Act: -0.0001

Data Index: 1061974 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.7954. Min Act: -0.0001

Data Index: 1224211 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.7722. Min Act: -0.0001

Data Index: 690416 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.7694. Min Act: -0.0001

Data Index: 1357492 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.7952. Min Act: -0.0001

Data Index: 1104366 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.8079. Min Act: -0.0001

Data Index: 883437 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.7402. Min Act: -0.0001

Data Index: 1189890 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.7667. Min Act: -0.0001

Data Index: 747561 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.7061. Min Act: -0.0001

Data Index: 308518 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.7084. Min Act: -0.0001

Data Index: 544600 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.6677. Min Act: -0.0001

Data Index: 1036669 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.7073. Min Act: -0.0001

Data Index: 1061368 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.7500. Min Act: -0.0001

Data Index: 1353138 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.6852. Min Act: -0.0001

Data Index: 638336 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.6885. Min Act: -0.0001

Data Index: 970259 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.6971. Min Act: -0.0001

Data Index: 1173300 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.6553. Min Act: -0.0001

Data Index: 103224 (C4 (Web Text))

Max Activating Token Index: 380