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

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

Neuron 2696 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: 1.0677. Min Range: -1.0677

Max Act: 1.0677. Min Act: -0.0001

Data Index: 347549 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 1.0677. Min Range: -1.0677

Max Act: 1.0188. Min Act: -0.0001

Data Index: 905612 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 1.0677. Min Range: -1.0677

Max Act: 1.0606. Min Act: -0.0001

Data Index: 1286515 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 1.0677. Min Range: -1.0677

Max Act: 0.9123. Min Act: -0.0001

Data Index: 409256 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 1.0677. Min Range: -1.0677

Max Act: 0.9070. Min Act: -0.0001

Data Index: 520455 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 1.0677. Min Range: -1.0677

Max Act: 0.8980. Min Act: -0.0001

Data Index: 82691 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 1.0677. Min Range: -1.0677

Max Act: 0.9511. Min Act: -0.0001

Data Index: 701755 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 1.0677. Min Range: -1.0677

Max Act: 0.8337. Min Act: -0.0001

Data Index: 676 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 1.0677. Min Range: -1.0677

Max Act: 0.8983. Min Act: -0.0001

Data Index: 156830 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 1.0677. Min Range: -1.0677

Max Act: 0.8500. Min Act: -0.0001

Data Index: 932005 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 1.0677. Min Range: -1.0677

Max Act: 0.8990. Min Act: -0.0001

Data Index: 974282 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 1.0677. Min Range: -1.0677

Max Act: 0.8533. Min Act: -0.0001

Data Index: 563176 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 1.0677. Min Range: -1.0677

Max Act: 0.8824. Min Act: -0.0001

Data Index: 665357 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 1.0677. Min Range: -1.0677

Max Act: 0.8260. Min Act: -0.0001

Data Index: 818375 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 1.0677. Min Range: -1.0677

Max Act: 0.8382. Min Act: -0.0001

Data Index: 1114776 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 1.0677. Min Range: -1.0677

Max Act: 0.8445. Min Act: -0.0001

Data Index: 296331 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 1.0677. Min Range: -1.0677

Max Act: 0.8828. Min Act: -0.0001

Data Index: 1154246 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 1.0677. Min Range: -1.0677

Max Act: 0.8496. Min Act: -0.0001

Data Index: 617310 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 1.0677. Min Range: -1.0677

Max Act: 0.8176. Min Act: -0.0001

Data Index: 157834 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 1.0677. Min Range: -1.0677

Max Act: 0.8132. Min Act: -0.0001

Data Index: 80787 (C4 (Web Text))

Max Activating Token Index: 459