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

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

Neuron 1872 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: 0.3928. Min Range: -0.3928

Max Act: 0.3291. Min Act: -0.0000

Data Index: 221273 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3237. Min Act: -0.0000

Data Index: 109097 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3567. Min Act: -0.0001

Data Index: 498761 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3545. Min Act: -0.0001

Data Index: 783030 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3746. Min Act: -0.0001

Data Index: 1307307 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3928. Min Act: -0.0000

Data Index: 429352 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3482. Min Act: -0.0000

Data Index: 1127828 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3396. Min Act: -0.0000

Data Index: 968891 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3103. Min Act: -0.0001

Data Index: 174339 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3288. Min Act: -0.0001

Data Index: 325009 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3195. Min Act: -0.0000

Data Index: 772583 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1232360 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3195. Min Act: -0.0000

Data Index: 294567 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1006759 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2900. Min Act: -0.0001

Data Index: 1076941 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2712. Min Act: -0.0000

Data Index: 870182 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2932. Min Act: -0.0000

Data Index: 452431 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3249. Min Act: -0.0001

Data Index: 469198 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2743. Min Act: -0.0001

Data Index: 131937 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2662. Min Act: -0.0001

Data Index: 1239936 (C4 (Web Text))

Max Activating Token Index: 488