Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2035 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.1935. Min Range: -5.1935

Max Act: 5.1935. Min Act: -0.1700

Data Index: 1205920 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 5.1935. Min Range: -5.1935

Max Act: 5.0685. Min Act: -0.1700

Data Index: 1133104 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 5.1935. Min Range: -5.1935

Max Act: 5.0060. Min Act: -0.1700

Data Index: 1171072 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 5.1935. Min Range: -5.1935

Max Act: 4.9747. Min Act: -0.1700

Data Index: 617356 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 5.1935. Min Range: -5.1935

Max Act: 4.9435. Min Act: -0.1700

Data Index: 1229167 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 5.1935. Min Range: -5.1935

Max Act: 4.8810. Min Act: -0.1700

Data Index: 695311 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 5.1935. Min Range: -5.1935

Max Act: 4.6935. Min Act: -0.1700

Data Index: 1026071 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 5.1935. Min Range: -5.1935

Max Act: 4.6935. Min Act: -0.1700

Data Index: 1311389 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 5.1935. Min Range: -5.1935

Max Act: 4.6622. Min Act: -0.1700

Data Index: 991401 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 5.1935. Min Range: -5.1935

Max Act: 4.7247. Min Act: -0.1700

Data Index: 636972 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 5.1935. Min Range: -5.1935

Max Act: 4.6310. Min Act: -0.1700

Data Index: 640401 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 5.1935. Min Range: -5.1935

Max Act: 4.6310. Min Act: -0.1700

Data Index: 931968 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 5.1935. Min Range: -5.1935

Max Act: 4.5997. Min Act: -0.1700

Data Index: 74473 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 5.1935. Min Range: -5.1935

Max Act: 4.5997. Min Act: -0.1700

Data Index: 973088 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 5.1935. Min Range: -5.1935

Max Act: 4.5685. Min Act: -0.1700

Data Index: 98905 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 5.1935. Min Range: -5.1935

Max Act: 4.5685. Min Act: -0.1700

Data Index: 620811 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 5.1935. Min Range: -5.1935

Max Act: 4.5372. Min Act: -0.1700

Data Index: 803126 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 5.1935. Min Range: -5.1935

Max Act: 4.5685. Min Act: -0.1700

Data Index: 1019891 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 5.1935. Min Range: -5.1935

Max Act: 4.4747. Min Act: -0.1700

Data Index: 409087 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 5.1935. Min Range: -5.1935

Max Act: 4.5372. Min Act: -0.1700

Data Index: 214005 (C4 (Web Text))

Max Activating Token Index: 578