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

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

Neuron 4074 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: 1.9711. Min Range: -1.9711

Max Act: 1.9711. Min Act: -0.0001

Data Index: 272694 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 1.9711. Min Range: -1.9711

Max Act: 1.8142. Min Act: -0.0001

Data Index: 239712 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 1.9711. Min Range: -1.9711

Max Act: 1.7099. Min Act: -0.0001

Data Index: 1021472 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 1.9711. Min Range: -1.9711

Max Act: 1.6947. Min Act: -0.0001

Data Index: 309292 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 1.9711. Min Range: -1.9711

Max Act: 1.6919. Min Act: -0.0001

Data Index: 772972 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 1.9711. Min Range: -1.9711

Max Act: 1.6708. Min Act: -0.0001

Data Index: 957371 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 1.9711. Min Range: -1.9711

Max Act: 1.5668. Min Act: -0.0001

Data Index: 955057 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 1.9711. Min Range: -1.9711

Max Act: 1.5965. Min Act: -0.0001

Data Index: 324940 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 1.9711. Min Range: -1.9711

Max Act: 1.5740. Min Act: -0.0001

Data Index: 341607 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 1.9711. Min Range: -1.9711

Max Act: 1.5513. Min Act: -0.0001

Data Index: 1320451 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 1.9711. Min Range: -1.9711

Max Act: 1.4032. Min Act: -0.0001

Data Index: 734104 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 1.9711. Min Range: -1.9711

Max Act: 1.4958. Min Act: -0.0001

Data Index: 798162 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 1.9711. Min Range: -1.9711

Max Act: 1.4916. Min Act: -0.0001

Data Index: 504076 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 1.9711. Min Range: -1.9711

Max Act: 1.4349. Min Act: -0.0001

Data Index: 913390 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 1.9711. Min Range: -1.9711

Max Act: 1.3278. Min Act: -0.0001

Data Index: 1334286 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 1.9711. Min Range: -1.9711

Max Act: 1.4799. Min Act: -0.0001

Data Index: 339378 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 1.9711. Min Range: -1.9711

Max Act: 1.3595. Min Act: -0.0001

Data Index: 452773 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 1.9711. Min Range: -1.9711

Max Act: 1.5215. Min Act: -0.0001

Data Index: 385416 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 1.9711. Min Range: -1.9711

Max Act: 1.4197. Min Act: -0.0001

Data Index: 491804 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 1.9711. Min Range: -1.9711

Max Act: 1.3532. Min Act: -0.0001

Data Index: 847085 (C4 (Web Text))

Max Activating Token Index: 413