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

Dataset: The Pile

Neuron 3072 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.9943. Min Act: -0.0000

Data Index: 1422693 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.9780. Min Act: -0.0000

Data Index: 1185198 (The Pile)

Max Activating Token Index: 853

Text #2

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.9750. Min Act: -0.0000

Data Index: 1371557 (The Pile)

Max Activating Token Index: 953

Text #3

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.7888. Min Act: -0.0000

Data Index: 98033 (The Pile)

Max Activating Token Index: 527

Text #4

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.6902. Min Act: -0.0000

Data Index: 1983959 (The Pile)

Max Activating Token Index: 73

Text #5

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.7463. Min Act: -0.0000

Data Index: 1264979 (The Pile)

Max Activating Token Index: 14

Text #6

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.6124. Min Act: -0.0000

Data Index: 1872163 (The Pile)

Max Activating Token Index: 520

Text #7

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.5686. Min Act: -0.0000

Data Index: 1420523 (The Pile)

Max Activating Token Index: 59

Text #8

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.6057. Min Act: -0.0000

Data Index: 1019867 (The Pile)

Max Activating Token Index: 161

Text #9

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.6087. Min Act: -0.0000

Data Index: 1719037 (The Pile)

Max Activating Token Index: 775

Text #10

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.5312. Min Act: -0.0000

Data Index: 657310 (The Pile)

Max Activating Token Index: 42

Text #11

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.3702. Min Act: -0.0000

Data Index: 389249 (The Pile)

Max Activating Token Index: 324

Text #12

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.4500. Min Act: -0.0000

Data Index: 1799956 (The Pile)

Max Activating Token Index: 150

Text #13

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.3713. Min Act: -0.0000

Data Index: 221880 (The Pile)

Max Activating Token Index: 325

Text #14

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.4449. Min Act: -0.0000

Data Index: 1115410 (The Pile)

Max Activating Token Index: 153

Text #15

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.4452. Min Act: -0.0000

Data Index: 78151 (The Pile)

Max Activating Token Index: 348

Text #16

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.5187. Min Act: -0.0000

Data Index: 1559949 (The Pile)

Max Activating Token Index: 59

Text #17

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.2137. Min Act: -0.0000

Data Index: 1780845 (The Pile)

Max Activating Token Index: 834

Text #18

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.3522. Min Act: -0.0000

Data Index: 1512824 (The Pile)

Max Activating Token Index: 33

Text #19

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.3842. Min Act: -0.0000

Data Index: 1558652 (The Pile)

Max Activating Token Index: 829