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

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

Neuron 221 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.8970. Min Act: -0.0001

Data Index: 129153 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.8494. Min Act: -0.0001

Data Index: 634205 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1330166 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7739. Min Act: -0.0001

Data Index: 1054940 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7659. Min Act: -0.0001

Data Index: 442978 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.8084. Min Act: -0.0001

Data Index: 1249518 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7024. Min Act: -0.0000

Data Index: 1277615 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.5993. Min Act: -0.0000

Data Index: 665052 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6376. Min Act: -0.0000

Data Index: 951978 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6286. Min Act: -0.0001

Data Index: 218611 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6061. Min Act: -0.0001

Data Index: 367351 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6509. Min Act: -0.0001

Data Index: 279233 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6288. Min Act: -0.0001

Data Index: 622427 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6048. Min Act: -0.0001

Data Index: 55392 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6661. Min Act: -0.0000

Data Index: 496424 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6830. Min Act: -0.0001

Data Index: 290727 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6167. Min Act: -0.0001

Data Index: 457858 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.5943. Min Act: -0.0001

Data Index: 1002958 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6128. Min Act: -0.0001

Data Index: 663467 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6054. Min Act: -0.0001

Data Index: 376635 (C4 (Web Text))

Max Activating Token Index: 593