Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1288 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3614. Min Act: -0.0001

Data Index: 52942 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3392. Min Act: -0.0001

Data Index: 316319 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3353. Min Act: -0.0001

Data Index: 159185 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3296. Min Act: -0.0001

Data Index: 881400 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3190. Min Act: -0.0001

Data Index: 1107754 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3147. Min Act: -0.0001

Data Index: 650519 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2979. Min Act: -0.0001

Data Index: 1306657 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3063. Min Act: -0.0001

Data Index: 1161291 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3020. Min Act: -0.0001

Data Index: 1136257 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2972. Min Act: -0.0001

Data Index: 793945 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2972. Min Act: -0.0001

Data Index: 465744 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2861. Min Act: -0.0001

Data Index: 109676 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2963. Min Act: -0.0001

Data Index: 549829 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2690. Min Act: -0.0001

Data Index: 648862 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2843. Min Act: -0.0001

Data Index: 121031 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2744. Min Act: -0.0001

Data Index: 1072830 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2724. Min Act: -0.0001

Data Index: 766745 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2726. Min Act: -0.0001

Data Index: 512490 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2741. Min Act: -0.0001

Data Index: 234924 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2758. Min Act: -0.0001

Data Index: 973410 (C4 (Web Text))

Max Activating Token Index: 33