Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 890 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.4405. Min Act: -0.0000

Data Index: 795823 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3374. Min Act: -0.0000

Data Index: 288072 (The Pile)

Max Activating Token Index: 716

Text #2

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3507. Min Act: -0.0000

Data Index: 885809 (The Pile)

Max Activating Token Index: 272

Text #3

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3484. Min Act: -0.0000

Data Index: 151405 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3315. Min Act: -0.0000

Data Index: 1081834 (The Pile)

Max Activating Token Index: 189

Text #5

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3099. Min Act: -0.0000

Data Index: 826399 (The Pile)

Max Activating Token Index: 101

Text #6

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3312. Min Act: -0.0000

Data Index: 343798 (The Pile)

Max Activating Token Index: 291

Text #7

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3179. Min Act: -0.0000

Data Index: 25084 (The Pile)

Max Activating Token Index: 152

Text #8

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1842415 (The Pile)

Max Activating Token Index: 1003

Text #9

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3225. Min Act: -0.0000

Data Index: 1746480 (The Pile)

Max Activating Token Index: 338

Text #10

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3220. Min Act: -0.0000

Data Index: 299301 (The Pile)

Max Activating Token Index: 227

Text #11

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3180. Min Act: -0.0000

Data Index: 1827284 (The Pile)

Max Activating Token Index: 571

Text #12

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3173. Min Act: -0.0000

Data Index: 855224 (The Pile)

Max Activating Token Index: 129

Text #13

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1026806 (The Pile)

Max Activating Token Index: 318

Text #14

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3257. Min Act: -0.0000

Data Index: 806876 (The Pile)

Max Activating Token Index: 274

Text #15

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1879494 (The Pile)

Max Activating Token Index: 82

Text #16

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1156502 (The Pile)

Max Activating Token Index: 79

Text #17

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1238073 (The Pile)

Max Activating Token Index: 127

Text #18

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.2960. Min Act: -0.0000

Data Index: 1936410 (The Pile)

Max Activating Token Index: 313

Text #19

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3022. Min Act: -0.0000

Data Index: 868214 (The Pile)

Max Activating Token Index: 595