Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1616 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.7296. Min Act: -0.0001

Data Index: 50281 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6942. Min Act: -0.0001

Data Index: 45530 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6965. Min Act: -0.0001

Data Index: 1105803 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6299. Min Act: -0.0001

Data Index: 372896 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6335. Min Act: -0.0001

Data Index: 686901 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5783. Min Act: -0.0001

Data Index: 593424 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5779. Min Act: -0.0001

Data Index: 693995 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5962. Min Act: -0.0001

Data Index: 1305606 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5192. Min Act: -0.0001

Data Index: 709342 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5327. Min Act: -0.0001

Data Index: 1045924 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5223. Min Act: -0.0001

Data Index: 249927 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5027. Min Act: -0.0001

Data Index: 1346166 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5143. Min Act: -0.0001

Data Index: 1290770 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5160. Min Act: -0.0001

Data Index: 394111 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5430. Min Act: -0.0001

Data Index: 112350 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4922. Min Act: -0.0001

Data Index: 276862 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5330. Min Act: -0.0001

Data Index: 1234756 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5035. Min Act: -0.0001

Data Index: 451752 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4710. Min Act: -0.0001

Data Index: 527329 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4851. Min Act: -0.0001

Data Index: 893582 (C4 (Web Text))

Max Activating Token Index: 630