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

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

Neuron 590 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: 0.3206. Min Range: -0.3206

Max Act: 0.3206. Min Act: -0.0001

Data Index: 330102 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.3141. Min Act: -0.0001

Data Index: 401865 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2907. Min Act: -0.0001

Data Index: 601757 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2987. Min Act: -0.0001

Data Index: 1056779 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2728. Min Act: -0.0001

Data Index: 338373 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2602. Min Act: -0.0001

Data Index: 927068 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2508. Min Act: -0.0001

Data Index: 1272435 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2664. Min Act: -0.0001

Data Index: 1133075 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2517. Min Act: -0.0001

Data Index: 970783 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2504. Min Act: -0.0001

Data Index: 135277 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2540. Min Act: -0.0001

Data Index: 701538 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2590. Min Act: -0.0001

Data Index: 1170693 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2455. Min Act: -0.0001

Data Index: 1213110 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2387. Min Act: -0.0001

Data Index: 615538 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2544. Min Act: -0.0001

Data Index: 1258313 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2460. Min Act: -0.0000

Data Index: 63621 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2452. Min Act: -0.0000

Data Index: 1229936 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2412. Min Act: -0.0001

Data Index: 130203 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2443. Min Act: -0.0001

Data Index: 59295 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2375. Min Act: -0.0001

Data Index: 965354 (C4 (Web Text))

Max Activating Token Index: 527