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

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

Neuron 5826 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.4973. Min Act: -0.0000

Data Index: 221544 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.4950. Min Act: -0.0000

Data Index: 1105392 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1107704 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.4158. Min Act: -0.0000

Data Index: 254466 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1094919 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.4444. Min Act: -0.0000

Data Index: 886240 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.4221. Min Act: -0.0000

Data Index: 281557 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.4360. Min Act: -0.0000

Data Index: 37679 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.4125. Min Act: -0.0000

Data Index: 685876 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.4152. Min Act: -0.0000

Data Index: 560375 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3964. Min Act: -0.0000

Data Index: 478073 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3893. Min Act: -0.0000

Data Index: 124152 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3739. Min Act: -0.0000

Data Index: 717754 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3852. Min Act: -0.0000

Data Index: 455456 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3749. Min Act: -0.0000

Data Index: 960026 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3881. Min Act: -0.0000

Data Index: 4371 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3828. Min Act: -0.0000

Data Index: 380894 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3834. Min Act: -0.0000

Data Index: 1118127 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3835. Min Act: -0.0000

Data Index: 885486 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3809. Min Act: -0.0000

Data Index: 1161106 (C4 (Web Text))

Max Activating Token Index: 943