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

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

Neuron 3933 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3877. Min Act: -0.0001

Data Index: 1194498 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.4007. Min Act: -0.0001

Data Index: 63858 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3154. Min Act: -0.0001

Data Index: 293670 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3048. Min Act: -0.0001

Data Index: 667477 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3062. Min Act: -0.0001

Data Index: 631043 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3130. Min Act: -0.0001

Data Index: 502546 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3124. Min Act: -0.0001

Data Index: 1022994 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3047. Min Act: -0.0001

Data Index: 739489 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3059. Min Act: -0.0001

Data Index: 64932 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.2953. Min Act: -0.0001

Data Index: 691186 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3025. Min Act: -0.0001

Data Index: 340439 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.2867. Min Act: -0.0001

Data Index: 1202759 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.2872. Min Act: -0.0001

Data Index: 815219 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.2870. Min Act: -0.0001

Data Index: 863458 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.2840. Min Act: -0.0001

Data Index: 914288 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.2553. Min Act: -0.0001

Data Index: 830255 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.2578. Min Act: -0.0001

Data Index: 601860 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.2567. Min Act: -0.0001

Data Index: 1254304 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.2687. Min Act: -0.0001

Data Index: 569042 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.2647. Min Act: -0.0001

Data Index: 318947 (C4 (Web Text))

Max Activating Token Index: 1010