Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2274 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8857. Min Range: -0.8857

Max Act: 0.8857. Min Act: -0.0000

Data Index: 425158 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.8857. Min Range: -0.8857

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1197392 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.8857. Min Range: -0.8857

Max Act: 0.5982. Min Act: -0.0000

Data Index: 851545 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 0.8857. Min Range: -0.8857

Max Act: 0.5213. Min Act: -0.0000

Data Index: 310184 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.8857. Min Range: -0.8857

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1241731 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.8857. Min Range: -0.8857

Max Act: 0.4818. Min Act: -0.0000

Data Index: 561794 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 0.8857. Min Range: -0.8857

Max Act: 0.5161. Min Act: -0.0000

Data Index: 316143 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.8857. Min Range: -0.8857

Max Act: 0.4936. Min Act: -0.0000

Data Index: 1275202 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.8857. Min Range: -0.8857

Max Act: 0.4860. Min Act: -0.0000

Data Index: 766402 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 0.8857. Min Range: -0.8857

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1293891 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 0.8857. Min Range: -0.8857

Max Act: 0.4480. Min Act: -0.0000

Data Index: 512206 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.8857. Min Range: -0.8857

Max Act: 0.4406. Min Act: -0.0000

Data Index: 741080 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 0.8857. Min Range: -0.8857

Max Act: 0.4435. Min Act: -0.0000

Data Index: 253095 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.8857. Min Range: -0.8857

Max Act: 0.4932. Min Act: -0.0000

Data Index: 314221 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 0.8857. Min Range: -0.8857

Max Act: 0.4655. Min Act: -0.0000

Data Index: 853186 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 0.8857. Min Range: -0.8857

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1162549 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.8857. Min Range: -0.8857

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1201206 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.8857. Min Range: -0.8857

Max Act: 0.4520. Min Act: -0.0000

Data Index: 949492 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.8857. Min Range: -0.8857

Max Act: 0.4587. Min Act: -0.0000

Data Index: 583794 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.8857. Min Range: -0.8857

Max Act: 0.4568. Min Act: -0.0000

Data Index: 984397 (C4 (Web Text))

Max Activating Token Index: 618