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

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

Neuron 5574 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4300. Min Range: -4.4300

Max Act: 4.1168. Min Act: -0.0001

Data Index: 743725 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 4.4300. Min Range: -4.4300

Max Act: 4.4277. Min Act: -0.0001

Data Index: 501112 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 4.4300. Min Range: -4.4300

Max Act: 4.4300. Min Act: -0.0001

Data Index: 896280 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 4.4300. Min Range: -4.4300

Max Act: 4.2398. Min Act: -0.0001

Data Index: 961892 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 4.4300. Min Range: -4.4300

Max Act: 4.2301. Min Act: -0.0001

Data Index: 845169 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 4.4300. Min Range: -4.4300

Max Act: 4.1801. Min Act: -0.0001

Data Index: 1341372 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 4.4300. Min Range: -4.4300

Max Act: 4.1371. Min Act: -0.0001

Data Index: 482982 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.9461. Min Act: -0.0001

Data Index: 201441 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.4728. Min Act: -0.0001

Data Index: 1216754 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.9344. Min Act: -0.0001

Data Index: 107767 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 4.4300. Min Range: -4.4300

Max Act: 4.2380. Min Act: -0.0001

Data Index: 791649 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.8439. Min Act: -0.0001

Data Index: 1263254 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.7390. Min Act: -0.0001

Data Index: 510223 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.7196. Min Act: -0.0001

Data Index: 1255246 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.7123. Min Act: -0.0001

Data Index: 213171 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.6920. Min Act: -0.0001

Data Index: 505629 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.4378. Min Act: -0.0001

Data Index: 63541 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.5803. Min Act: -0.0001

Data Index: 437180 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.7154. Min Act: -0.0001

Data Index: 212755 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 4.4300. Min Range: -4.4300

Max Act: 3.3640. Min Act: -0.0001

Data Index: 229796 (C4 (Web Text))

Max Activating Token Index: 96