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

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

Neuron 4555 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5732. Min Range: -6.5732

Max Act: 6.5732. Min Act: -0.0000

Data Index: 574731 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 6.5732. Min Range: -6.5732

Max Act: 5.2428. Min Act: -0.0000

Data Index: 854480 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 6.5732. Min Range: -6.5732

Max Act: 5.1270. Min Act: -0.0000

Data Index: 1324878 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 6.5732. Min Range: -6.5732

Max Act: 5.0451. Min Act: -0.0000

Data Index: 1136072 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 6.5732. Min Range: -6.5732

Max Act: 4.8419. Min Act: -0.0000

Data Index: 1313467 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 6.5732. Min Range: -6.5732

Max Act: 4.3059. Min Act: -0.0000

Data Index: 348808 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 6.5732. Min Range: -6.5732

Max Act: 4.4197. Min Act: -0.0000

Data Index: 1127617 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 6.5732. Min Range: -6.5732

Max Act: 4.4047. Min Act: -0.0000

Data Index: 340456 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 6.5732. Min Range: -6.5732

Max Act: 4.4922. Min Act: -0.0000

Data Index: 922939 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 6.5732. Min Range: -6.5732

Max Act: 4.2874. Min Act: -0.0000

Data Index: 822918 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 6.5732. Min Range: -6.5732

Max Act: 4.2695. Min Act: -0.0000

Data Index: 932225 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 6.5732. Min Range: -6.5732

Max Act: 4.2408. Min Act: -0.0000

Data Index: 1208373 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 6.5732. Min Range: -6.5732

Max Act: 4.2437. Min Act: -0.0000

Data Index: 150904 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 6.5732. Min Range: -6.5732

Max Act: 4.2339. Min Act: -0.0000

Data Index: 1335529 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 6.5732. Min Range: -6.5732

Max Act: 4.2140. Min Act: -0.0000

Data Index: 1218092 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 6.5732. Min Range: -6.5732

Max Act: 4.1747. Min Act: -0.0000

Data Index: 1262745 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 6.5732. Min Range: -6.5732

Max Act: 4.0464. Min Act: -0.0000

Data Index: 457513 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 6.5732. Min Range: -6.5732

Max Act: 3.9791. Min Act: -0.0000

Data Index: 228130 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 6.5732. Min Range: -6.5732

Max Act: 4.1444. Min Act: -0.0000

Data Index: 718125 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 6.5732. Min Range: -6.5732

Max Act: 4.1095. Min Act: -0.0000

Data Index: 1485927 (Python Code)

Max Activating Token Index: 319