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

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

Neuron 2416 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.6333. Min Act: -0.0000

Data Index: 368723 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.5756. Min Act: -0.0000

Data Index: 586545 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.5126. Min Act: -0.0001

Data Index: 288990 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4831. Min Act: -0.0000

Data Index: 1205137 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4619. Min Act: -0.0001

Data Index: 226225 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4760. Min Act: -0.0000

Data Index: 69398 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4685. Min Act: -0.0001

Data Index: 1003481 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4472. Min Act: -0.0001

Data Index: 1230302 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4420. Min Act: -0.0001

Data Index: 12818 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4384. Min Act: -0.0000

Data Index: 588203 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4341. Min Act: -0.0001

Data Index: 973040 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4299. Min Act: -0.0000

Data Index: 825089 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4160. Min Act: -0.0001

Data Index: 221366 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4126. Min Act: -0.0000

Data Index: 97209 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4137. Min Act: -0.0000

Data Index: 311258 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4120. Min Act: -0.0000

Data Index: 668140 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4002. Min Act: -0.0000

Data Index: 272672 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.4132. Min Act: -0.0000

Data Index: 640183 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.3964. Min Act: -0.0001

Data Index: 219767 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.6333. Min Range: -0.6333

Max Act: 0.3944. Min Act: -0.0000

Data Index: 802971 (C4 (Web Text))

Max Activating Token Index: 587