Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 281 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.8424. Min Range: -5.8424

Max Act: 5.8424. Min Act: -0.0001

Data Index: 524134 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 5.8424. Min Range: -5.8424

Max Act: 5.0286. Min Act: -0.0001

Data Index: 344304 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 5.8424. Min Range: -5.8424

Max Act: 4.7785. Min Act: -0.0001

Data Index: 772026 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 5.8424. Min Range: -5.8424

Max Act: 4.7638. Min Act: -0.0001

Data Index: 203695 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 5.8424. Min Range: -5.8424

Max Act: 4.5581. Min Act: -0.0001

Data Index: 1264983 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 5.8424. Min Range: -5.8424

Max Act: 4.5304. Min Act: -0.0001

Data Index: 933885 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 5.8424. Min Range: -5.8424

Max Act: 4.4772. Min Act: -0.0001

Data Index: 205243 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 5.8424. Min Range: -5.8424

Max Act: 4.3795. Min Act: -0.0001

Data Index: 1136984 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 5.8424. Min Range: -5.8424

Max Act: 4.3024. Min Act: -0.0001

Data Index: 996956 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 5.8424. Min Range: -5.8424

Max Act: 4.2457. Min Act: -0.0001

Data Index: 791185 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 5.8424. Min Range: -5.8424

Max Act: 4.2361. Min Act: -0.0001

Data Index: 949743 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 5.8424. Min Range: -5.8424

Max Act: 4.2384. Min Act: -0.0001

Data Index: 49922 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 5.8424. Min Range: -5.8424

Max Act: 4.5574. Min Act: -0.0001

Data Index: 1324650 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 5.8424. Min Range: -5.8424

Max Act: 4.3640. Min Act: -0.0001

Data Index: 40436 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 5.8424. Min Range: -5.8424

Max Act: 4.3493. Min Act: -0.0001

Data Index: 302696 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 5.8424. Min Range: -5.8424

Max Act: 4.3299. Min Act: -0.0001

Data Index: 191413 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 5.8424. Min Range: -5.8424

Max Act: 3.9577. Min Act: -0.0001

Data Index: 445141 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 5.8424. Min Range: -5.8424

Max Act: 3.9598. Min Act: -0.0001

Data Index: 739656 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 5.8424. Min Range: -5.8424

Max Act: 3.9185. Min Act: -0.0001

Data Index: 1336004 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 5.8424. Min Range: -5.8424

Max Act: 4.2366. Min Act: -0.0001

Data Index: 721476 (C4 (Web Text))

Max Activating Token Index: 375