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

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

Neuron 2320 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.5552. Min Act: -0.0000

Data Index: 1009287 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4613. Min Act: -0.0000

Data Index: 663358 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1091040 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4545. Min Act: -0.0000

Data Index: 33900 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3984. Min Act: -0.0000

Data Index: 162591 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3903. Min Act: -0.0000

Data Index: 1318097 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3823. Min Act: -0.0000

Data Index: 298319 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3724. Min Act: -0.0000

Data Index: 880479 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3272. Min Act: -0.0000

Data Index: 105284 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3547. Min Act: -0.0000

Data Index: 939912 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3471. Min Act: -0.0000

Data Index: 695649 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3353. Min Act: -0.0000

Data Index: 1089813 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3231. Min Act: -0.0000

Data Index: 1097893 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3047. Min Act: -0.0000

Data Index: 566208 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3306. Min Act: -0.0000

Data Index: 192098 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3206. Min Act: -0.0000

Data Index: 210772 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3262. Min Act: -0.0001

Data Index: 947403 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1213337 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.2939. Min Act: -0.0001

Data Index: 510599 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3315. Min Act: -0.0001

Data Index: 1122115 (C4 (Web Text))

Max Activating Token Index: 328