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

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

Neuron 2543 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9348. Min Range: -3.9348

Max Act: 3.9348. Min Act: -0.0001

Data Index: 698569 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 3.9348. Min Range: -3.9348

Max Act: 3.0228. Min Act: -0.0001

Data Index: 412799 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 3.9348. Min Range: -3.9348

Max Act: 2.5681. Min Act: -0.0001

Data Index: 854211 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 3.9348. Min Range: -3.9348

Max Act: 2.9533. Min Act: -0.0001

Data Index: 1191715 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 3.9348. Min Range: -3.9348

Max Act: 2.7352. Min Act: -0.0001

Data Index: 41361 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 3.9348. Min Range: -3.9348

Max Act: 2.8444. Min Act: -0.0001

Data Index: 1255323 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 3.9348. Min Range: -3.9348

Max Act: 2.4943. Min Act: -0.0001

Data Index: 735630 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 3.9348. Min Range: -3.9348

Max Act: 2.6135. Min Act: -0.0001

Data Index: 267047 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 3.9348. Min Range: -3.9348

Max Act: 2.7429. Min Act: -0.0001

Data Index: 11264 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 3.9348. Min Range: -3.9348

Max Act: 2.6019. Min Act: -0.0001

Data Index: 215504 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 3.9348. Min Range: -3.9348

Max Act: 2.4427. Min Act: -0.0001

Data Index: 686714 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 3.9348. Min Range: -3.9348

Max Act: 2.2935. Min Act: -0.0001

Data Index: 809543 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 3.9348. Min Range: -3.9348

Max Act: 2.5459. Min Act: -0.0001

Data Index: 804217 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 3.9348. Min Range: -3.9348

Max Act: 2.5246. Min Act: -0.0001

Data Index: 1191962 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 3.9348. Min Range: -3.9348

Max Act: 2.6613. Min Act: -0.0001

Data Index: 1156566 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 3.9348. Min Range: -3.9348

Max Act: 2.6460. Min Act: -0.0001

Data Index: 1293630 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 3.9348. Min Range: -3.9348

Max Act: 2.5056. Min Act: -0.0001

Data Index: 1056701 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 3.9348. Min Range: -3.9348

Max Act: 2.4986. Min Act: -0.0001

Data Index: 1057747 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 3.9348. Min Range: -3.9348

Max Act: 2.4912. Min Act: -0.0001

Data Index: 897087 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 3.9348. Min Range: -3.9348

Max Act: 2.3708. Min Act: -0.0001

Data Index: 575202 (C4 (Web Text))

Max Activating Token Index: 820