Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1808 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.3091. Min Act: -0.1700

Data Index: 173026 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.2777. Min Act: -0.1700

Data Index: 19434 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.2934. Min Act: -0.1700

Data Index: 719093 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.2777. Min Act: -0.1700

Data Index: 1102549 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.2620. Min Act: -0.1700

Data Index: 272144 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.2620. Min Act: -0.1700

Data Index: 1246995 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.2463. Min Act: -0.1700

Data Index: 1190715 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.2306. Min Act: -0.1700

Data Index: 1311195 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.2306. Min Act: -0.1700

Data Index: 670915 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.2148. Min Act: -0.1700

Data Index: 1114598 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.2148. Min Act: -0.1700

Data Index: 1261563 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.1991. Min Act: -0.1700

Data Index: 503983 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.2148. Min Act: -0.1700

Data Index: 1030240 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.1991. Min Act: -0.1700

Data Index: 82935 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.1991. Min Act: -0.1700

Data Index: 126252 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.1991. Min Act: -0.1700

Data Index: 625974 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.1834. Min Act: -0.1700

Data Index: 1337376 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.1834. Min Act: -0.1700

Data Index: 199593 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.1676. Min Act: -0.1700

Data Index: 1054828 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.1519. Min Act: -0.1700

Data Index: 228419 (C4 (Web Text))

Max Activating Token Index: 156