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

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

Neuron 2367 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2507. Min Range: -1.2507

Max Act: 1.2507. Min Act: -0.0001

Data Index: 348390 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 1.2507. Min Range: -1.2507

Max Act: 1.1668. Min Act: -0.0000

Data Index: 35056 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 1.2507. Min Range: -1.2507

Max Act: 1.1509. Min Act: -0.0000

Data Index: 626882 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 1.2507. Min Range: -1.2507

Max Act: 1.0205. Min Act: -0.0000

Data Index: 272137 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.9505. Min Act: -0.0000

Data Index: 500706 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.9163. Min Act: -0.0000

Data Index: 1223581 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.9356. Min Act: -0.0000

Data Index: 1018757 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.9478. Min Act: -0.0001

Data Index: 895283 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.9350. Min Act: -0.0000

Data Index: 690825 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.8554. Min Act: -0.0000

Data Index: 397709 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.8774. Min Act: -0.0000

Data Index: 1285419 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.7906. Min Act: -0.0000

Data Index: 459959 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.8165. Min Act: -0.0000

Data Index: 889622 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.8099. Min Act: -0.0001

Data Index: 537069 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.8378. Min Act: -0.0000

Data Index: 1105502 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.8097. Min Act: -0.0000

Data Index: 416656 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.8234. Min Act: -0.0000

Data Index: 73815 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.7645. Min Act: -0.0000

Data Index: 980481 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.8059. Min Act: -0.0000

Data Index: 448652 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.7584. Min Act: -0.0000

Data Index: 989282 (C4 (Web Text))

Max Activating Token Index: 477