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

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

Neuron 4053 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7134. Min Range: -5.7134

Max Act: 5.7134. Min Act: -0.0000

Data Index: 13451 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 5.7134. Min Range: -5.7134

Max Act: 5.3161. Min Act: -0.0000

Data Index: 42691 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 5.7134. Min Range: -5.7134

Max Act: 5.3423. Min Act: -0.0000

Data Index: 946512 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 5.7134. Min Range: -5.7134

Max Act: 5.0801. Min Act: -0.0000

Data Index: 575354 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 5.7134. Min Range: -5.7134

Max Act: 5.0258. Min Act: -0.0000

Data Index: 1276180 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 5.7134. Min Range: -5.7134

Max Act: 4.8567. Min Act: -0.0000

Data Index: 148834 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 5.7134. Min Range: -5.7134

Max Act: 4.2637. Min Act: -0.0000

Data Index: 1043823 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 5.7134. Min Range: -5.7134

Max Act: 4.3246. Min Act: -0.0000

Data Index: 1318431 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 5.7134. Min Range: -5.7134

Max Act: 4.1450. Min Act: -0.0000

Data Index: 843088 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 5.7134. Min Range: -5.7134

Max Act: 4.3450. Min Act: -0.0000

Data Index: 744675 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 5.7134. Min Range: -5.7134

Max Act: 4.1125. Min Act: -0.0000

Data Index: 467627 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 5.7134. Min Range: -5.7134

Max Act: 4.2564. Min Act: -0.0000

Data Index: 546027 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 5.7134. Min Range: -5.7134

Max Act: 3.7700. Min Act: -0.0000

Data Index: 581221 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 5.7134. Min Range: -5.7134

Max Act: 3.8978. Min Act: -0.0000

Data Index: 1338165 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 5.7134. Min Range: -5.7134

Max Act: 3.7590. Min Act: -0.0000

Data Index: 741999 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 5.7134. Min Range: -5.7134

Max Act: 3.9132. Min Act: -0.0000

Data Index: 1270480 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 5.7134. Min Range: -5.7134

Max Act: 3.5529. Min Act: -0.0000

Data Index: 108646 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 5.7134. Min Range: -5.7134

Max Act: 4.0551. Min Act: -0.0000

Data Index: 255045 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 5.7134. Min Range: -5.7134

Max Act: 3.6813. Min Act: -0.0000

Data Index: 1305046 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 5.7134. Min Range: -5.7134

Max Act: 3.8336. Min Act: -0.0000

Data Index: 861620 (C4 (Web Text))

Max Activating Token Index: 830