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

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

Neuron 2539 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.6756. Min Act: -0.0004

Data Index: 929796 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.6912. Min Act: -0.0003

Data Index: 174073 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.6026. Min Act: -0.0003

Data Index: 459722 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5968. Min Act: -0.0003

Data Index: 1324350 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5542. Min Act: -0.0003

Data Index: 1004448 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5703. Min Act: -0.0003

Data Index: 864120 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5745. Min Act: -0.0003

Data Index: 678251 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5173. Min Act: -0.0003

Data Index: 983908 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5239. Min Act: -0.0003

Data Index: 589053 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4861. Min Act: -0.0003

Data Index: 607381 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5160. Min Act: -0.0003

Data Index: 628490 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5300. Min Act: -0.0003

Data Index: 215320 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4823. Min Act: -0.0003

Data Index: 860670 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5071. Min Act: -0.0003

Data Index: 749620 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4551. Min Act: -0.0003

Data Index: 70111 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4835. Min Act: -0.0003

Data Index: 85440 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5140. Min Act: -0.0003

Data Index: 330835 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5147. Min Act: -0.0003

Data Index: 1312832 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5295. Min Act: -0.0003

Data Index: 970196 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4951. Min Act: -0.0003

Data Index: 176931 (C4 (Web Text))

Max Activating Token Index: 371