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

Dataset: The Pile

Neuron 2183 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.3019. Min Act: -0.0000

Data Index: 1799489 (The Pile)

Max Activating Token Index: 790

Text #1

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2921. Min Act: -0.0000

Data Index: 243496 (The Pile)

Max Activating Token Index: 842

Text #2

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2505. Min Act: -0.0000

Data Index: 546758 (The Pile)

Max Activating Token Index: 144

Text #3

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2638. Min Act: -0.0000

Data Index: 333830 (The Pile)

Max Activating Token Index: 274

Text #4

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2148. Min Act: -0.0000

Data Index: 1760320 (The Pile)

Max Activating Token Index: 761

Text #5

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2344. Min Act: -0.0000

Data Index: 70248 (The Pile)

Max Activating Token Index: 918

Text #6

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2361. Min Act: -0.0000

Data Index: 1930984 (The Pile)

Max Activating Token Index: 702

Text #7

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2273. Min Act: -0.0000

Data Index: 247173 (The Pile)

Max Activating Token Index: 108

Text #8

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2284. Min Act: -0.0000

Data Index: 474043 (The Pile)

Max Activating Token Index: 447

Text #9

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2271. Min Act: -0.0000

Data Index: 63869 (The Pile)

Max Activating Token Index: 404

Text #10

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2464. Min Act: -0.0000

Data Index: 1508370 (The Pile)

Max Activating Token Index: 138

Text #11

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2278. Min Act: -0.0000

Data Index: 1098904 (The Pile)

Max Activating Token Index: 534

Text #12

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2290. Min Act: -0.0000

Data Index: 1346811 (The Pile)

Max Activating Token Index: 549

Text #13

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2100. Min Act: -0.0000

Data Index: 134654 (The Pile)

Max Activating Token Index: 380

Text #14

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2250. Min Act: -0.0000

Data Index: 188242 (The Pile)

Max Activating Token Index: 407

Text #15

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2174. Min Act: -0.0000

Data Index: 153721 (The Pile)

Max Activating Token Index: 630

Text #16

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2097. Min Act: -0.0000

Data Index: 658027 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2163. Min Act: -0.0000

Data Index: 222261 (The Pile)

Max Activating Token Index: 55

Text #18

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.1987. Min Act: -0.0000

Data Index: 1336664 (The Pile)

Max Activating Token Index: 905

Text #19

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2131. Min Act: -0.0000

Data Index: 197460 (The Pile)

Max Activating Token Index: 520