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

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

Neuron 3618 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.8477. Min Act: -0.0001

Data Index: 1052315 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.8455. Min Act: -0.0000

Data Index: 86274 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.7871. Min Act: -0.0000

Data Index: 855110 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.7950. Min Act: -0.0001

Data Index: 15037 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.8472. Min Act: -0.0001

Data Index: 981944 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.7565. Min Act: -0.0001

Data Index: 540420 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.7024. Min Act: -0.0001

Data Index: 379453 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.7293. Min Act: -0.0000

Data Index: 1213179 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.7164. Min Act: -0.0001

Data Index: 278405 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.7306. Min Act: -0.0001

Data Index: 618930 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.6694. Min Act: -0.0001

Data Index: 919559 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.6466. Min Act: -0.0000

Data Index: 59182 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.6763. Min Act: -0.0001

Data Index: 165513 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.6803. Min Act: -0.0001

Data Index: 570994 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.6319. Min Act: -0.0001

Data Index: 373521 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.6032. Min Act: -0.0000

Data Index: 383406 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.5991. Min Act: -0.0000

Data Index: 785695 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.5900. Min Act: -0.0001

Data Index: 990988 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1014479 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.5763. Min Act: -0.0000

Data Index: 453963 (C4 (Web Text))

Max Activating Token Index: 861