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

Dataset: The Pile

Neuron 2189 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.8391. Min Act: -0.0000

Data Index: 1782961 (The Pile)

Max Activating Token Index: 609

Text #1

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.8938. Min Act: -0.0000

Data Index: 613634 (The Pile)

Max Activating Token Index: 639

Text #2

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.9151. Min Act: -0.0000

Data Index: 583711 (The Pile)

Max Activating Token Index: 661

Text #3

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7519. Min Act: -0.0000

Data Index: 1378120 (The Pile)

Max Activating Token Index: 703

Text #4

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7903. Min Act: -0.0000

Data Index: 1177139 (The Pile)

Max Activating Token Index: 372

Text #5

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1685658 (The Pile)

Max Activating Token Index: 170

Text #6

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7990. Min Act: -0.0000

Data Index: 215659 (The Pile)

Max Activating Token Index: 258

Text #7

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1431970 (The Pile)

Max Activating Token Index: 425

Text #8

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7111. Min Act: -0.0000

Data Index: 1552029 (The Pile)

Max Activating Token Index: 113

Text #9

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7374. Min Act: -0.0000

Data Index: 307785 (The Pile)

Max Activating Token Index: 125

Text #10

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7347. Min Act: -0.0000

Data Index: 1904176 (The Pile)

Max Activating Token Index: 880

Text #11

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7845. Min Act: -0.0000

Data Index: 911140 (The Pile)

Max Activating Token Index: 183

Text #12

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7267. Min Act: -0.0000

Data Index: 1584253 (The Pile)

Max Activating Token Index: 36

Text #13

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1869969 (The Pile)

Max Activating Token Index: 243

Text #14

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7334. Min Act: -0.0000

Data Index: 1854796 (The Pile)

Max Activating Token Index: 74

Text #15

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7516. Min Act: -0.0000

Data Index: 250817 (The Pile)

Max Activating Token Index: 102

Text #16

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1182598 (The Pile)

Max Activating Token Index: 394

Text #17

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7266. Min Act: -0.0000

Data Index: 720154 (The Pile)

Max Activating Token Index: 406

Text #18

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7228. Min Act: -0.0000

Data Index: 318929 (The Pile)

Max Activating Token Index: 34

Text #19

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7166. Min Act: -0.0000

Data Index: 1859356 (The Pile)

Max Activating Token Index: 204