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

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

Neuron 3977 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0426. Min Range: -1.0426

Max Act: 1.0426. Min Act: -0.0001

Data Index: 638302 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.9903. Min Act: -0.0001

Data Index: 319422 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.9040. Min Act: -0.0001

Data Index: 839161 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.7487. Min Act: -0.0001

Data Index: 8818 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.8653. Min Act: -0.0001

Data Index: 747109 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.7257. Min Act: -0.0001

Data Index: 1226309 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.7997. Min Act: -0.0001

Data Index: 111343 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.8291. Min Act: -0.0001

Data Index: 1136900 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.6212. Min Act: -0.0001

Data Index: 14602 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.9141. Min Act: -0.0001

Data Index: 550186 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.7404. Min Act: -0.0000

Data Index: 75395 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.7384. Min Act: -0.0001

Data Index: 1101109 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.6416. Min Act: -0.0001

Data Index: 12719 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.6794. Min Act: -0.0001

Data Index: 929379 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.7864. Min Act: -0.0001

Data Index: 711167 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.7155. Min Act: -0.0001

Data Index: 100479 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.5650. Min Act: -0.0001

Data Index: 489257 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.7515. Min Act: -0.0001

Data Index: 43807 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.7221. Min Act: -0.0001

Data Index: 1173819 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 1.0426. Min Range: -1.0426

Max Act: 0.8034. Min Act: -0.0001

Data Index: 822857 (C4 (Web Text))

Max Activating Token Index: 486