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

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

Neuron 2455 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0121. Min Range: -1.0121

Max Act: 1.0121. Min Act: -0.0001

Data Index: 504046 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.6360. Min Act: -0.0000

Data Index: 23348 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.5475. Min Act: -0.0001

Data Index: 154275 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.4973. Min Act: -0.0001

Data Index: 873296 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.4798. Min Act: -0.0000

Data Index: 1119172 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1031993 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.4848. Min Act: -0.0001

Data Index: 638637 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.4895. Min Act: -0.0001

Data Index: 1228795 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.4987. Min Act: -0.0000

Data Index: 811803 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.4748. Min Act: -0.0000

Data Index: 861232 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.4138. Min Act: -0.0001

Data Index: 1192683 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.4270. Min Act: -0.0001

Data Index: 1139620 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.3873. Min Act: -0.0000

Data Index: 297680 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.4360. Min Act: -0.0001

Data Index: 273731 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.3996. Min Act: -0.0001

Data Index: 992609 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.3912. Min Act: -0.0001

Data Index: 493742 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.3778. Min Act: -0.0001

Data Index: 106843 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.3830. Min Act: -0.0001

Data Index: 374960 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.3570. Min Act: -0.0001

Data Index: 713591 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.3861. Min Act: -0.0001

Data Index: 386764 (C4 (Web Text))

Max Activating Token Index: 692