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

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

Neuron 2329 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.3288. Min Act: -0.0001

Data Index: 922216 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.2715. Min Act: -0.0000

Data Index: 220998 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.2881. Min Act: -0.0001

Data Index: 83057 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.0724. Min Act: -0.0000

Data Index: 1063470 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.1617. Min Act: -0.0001

Data Index: 1197936 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 1.3288. Min Range: -1.3288

Max Act: 0.9719. Min Act: -0.0000

Data Index: 816666 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 1.3288. Min Range: -1.3288

Max Act: 0.9451. Min Act: -0.0000

Data Index: 656267 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 1.3288. Min Range: -1.3288

Max Act: 0.8191. Min Act: -0.0000

Data Index: 1095508 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 1.3288. Min Range: -1.3288

Max Act: 0.8239. Min Act: -0.0000

Data Index: 287628 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 1.3288. Min Range: -1.3288

Max Act: 0.8949. Min Act: -0.0001

Data Index: 117811 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 1.3288. Min Range: -1.3288

Max Act: 0.8679. Min Act: -0.0001

Data Index: 200883 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 1.3288. Min Range: -1.3288

Max Act: 0.7893. Min Act: -0.0001

Data Index: 253608 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 1.3288. Min Range: -1.3288

Max Act: 0.8165. Min Act: -0.0000

Data Index: 855852 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 1.3288. Min Range: -1.3288

Max Act: 0.7683. Min Act: -0.0000

Data Index: 875949 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 1.3288. Min Range: -1.3288

Max Act: 0.7418. Min Act: -0.0001

Data Index: 1046315 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 1.3288. Min Range: -1.3288

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1078671 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 1.3288. Min Range: -1.3288

Max Act: 0.7475. Min Act: 0.0000

Data Index: 920027 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 1.3288. Min Range: -1.3288

Max Act: 0.7081. Min Act: -0.0001

Data Index: 183360 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 1.3288. Min Range: -1.3288

Max Act: 0.7133. Min Act: -0.0001

Data Index: 197163 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 1.3288. Min Range: -1.3288

Max Act: 0.6974. Min Act: -0.0000

Data Index: 519186 (C4 (Web Text))

Max Activating Token Index: 263