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

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

Neuron 2546 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5410. Min Act: -0.0001

Data Index: 582688 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.6458. Min Act: -0.0001

Data Index: 1203736 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5923. Min Act: -0.0001

Data Index: 889548 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5546. Min Act: -0.0001

Data Index: 1042351 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5397. Min Act: -0.0001

Data Index: 1040012 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5154. Min Act: -0.0001

Data Index: 450450 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5251. Min Act: -0.0001

Data Index: 5819 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5293. Min Act: -0.0001

Data Index: 225732 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4974. Min Act: -0.0001

Data Index: 83739 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4824. Min Act: -0.0001

Data Index: 347647 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4971. Min Act: -0.0001

Data Index: 1150445 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4630. Min Act: -0.0001

Data Index: 1302095 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4926. Min Act: -0.0001

Data Index: 951025 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5234. Min Act: -0.0001

Data Index: 136117 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4712. Min Act: -0.0001

Data Index: 1070174 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4983. Min Act: -0.0001

Data Index: 170693 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4730. Min Act: -0.0001

Data Index: 594761 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4603. Min Act: -0.0001

Data Index: 820235 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4595. Min Act: -0.0001

Data Index: 1261608 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4943. Min Act: -0.0001

Data Index: 801692 (C4 (Web Text))

Max Activating Token Index: 301