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

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

Neuron 2803 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: 1.9705. Min Range: -1.9705

Max Act: 1.9705. Min Act: -0.0001

Data Index: 1247178 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.6890. Min Act: -0.0001

Data Index: 965165 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.5085. Min Act: -0.0001

Data Index: 262296 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.5164. Min Act: -0.0001

Data Index: 247525 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.5886. Min Act: -0.0001

Data Index: 1219810 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.4925. Min Act: -0.0001

Data Index: 138026 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.4182. Min Act: -0.0001

Data Index: 1128352 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.2929. Min Act: -0.0001

Data Index: 546782 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.3755. Min Act: -0.0001

Data Index: 494217 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.2440. Min Act: -0.0001

Data Index: 489662 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.3545. Min Act: -0.0001

Data Index: 723427 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.3494. Min Act: -0.0001

Data Index: 415371 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.3403. Min Act: -0.0001

Data Index: 246552 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.3367. Min Act: -0.0001

Data Index: 1263307 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.2637. Min Act: -0.0001

Data Index: 1227073 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.2012. Min Act: -0.0001

Data Index: 208830 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.2594. Min Act: -0.0001

Data Index: 835754 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.4214. Min Act: -0.0001

Data Index: 258680 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.2793. Min Act: -0.0001

Data Index: 192481 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.3543. Min Act: -0.0001

Data Index: 1256208 (C4 (Web Text))

Max Activating Token Index: 367