Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2026 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.0996. Min Range: -2.0996

Max Act: 2.0996. Min Act: -0.1700

Data Index: 8655502 (Open Web Text)

Max Activating Token Index: 423

Text #1

Max Range: 2.0996. Min Range: -2.0996

Max Act: 1.9973. Min Act: -0.1700

Data Index: 3801786 (Open Web Text)

Max Activating Token Index: 591

Text #2

Max Range: 2.0996. Min Range: -2.0996

Max Act: 2.0046. Min Act: -0.1700

Data Index: 8019911 (Open Web Text)

Max Activating Token Index: 378

Text #3

Max Range: 2.0996. Min Range: -2.0996

Max Act: 1.9874. Min Act: -0.1700

Data Index: 4420749 (Open Web Text)

Max Activating Token Index: 268

Text #4

Max Range: 2.0996. Min Range: -2.0996

Max Act: 1.9866. Min Act: -0.1700

Data Index: 5256271 (Open Web Text)

Max Activating Token Index: 191

Text #5

Max Range: 2.0996. Min Range: -2.0996

Max Act: 1.9819. Min Act: -0.1700

Data Index: 3592198 (Open Web Text)

Max Activating Token Index: 685

Text #6

Max Range: 2.0996. Min Range: -2.0996

Max Act: 1.9427. Min Act: -0.1700

Data Index: 4398162 (Open Web Text)

Max Activating Token Index: 53

Text #7

Max Range: 2.0996. Min Range: -2.0996

Max Act: 1.9467. Min Act: -0.1700

Data Index: 4602294 (Open Web Text)

Max Activating Token Index: 1005

Text #8

Max Range: 2.0996. Min Range: -2.0996

Max Act: 1.9612. Min Act: -0.1700

Data Index: 6089641 (Open Web Text)

Max Activating Token Index: 278

Text #9

Max Range: 2.0996. Min Range: -2.0996

Max Act: 1.9367. Min Act: -0.1700

Data Index: 4158122 (Open Web Text)

Max Activating Token Index: 511

Text #10

Max Range: 2.0996. Min Range: -2.0996

Max Act: 1.9455. Min Act: -0.1700

Data Index: 3251678 (Open Web Text)

Max Activating Token Index: 103

Text #11

Max Range: 2.0996. Min Range: -2.0996

Max Act: 1.9224. Min Act: -0.1700

Data Index: 4938962 (Open Web Text)

Max Activating Token Index: 535

Text #12

Max Range: 2.0996. Min Range: -2.0996

Max Act: 1.9286. Min Act: -0.1700

Data Index: 2337838 (Open Web Text)

Max Activating Token Index: 380

Text #13

Max Range: 2.0996. Min Range: -2.0996

Max Act: 1.9155. Min Act: -0.1700

Data Index: 7812383 (Open Web Text)

Max Activating Token Index: 105

Text #14

Max Range: 2.0996. Min Range: -2.0996

Max Act: 1.9173. Min Act: -0.1700

Data Index: 2005889 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 2.0996. Min Range: -2.0996

Max Act: 1.9237. Min Act: -0.1700

Data Index: 3148390 (Open Web Text)

Max Activating Token Index: 246

Text #16

Max Range: 2.0996. Min Range: -2.0996

Max Act: 1.9208. Min Act: -0.1700

Data Index: 6323158 (Open Web Text)

Max Activating Token Index: 91

Text #17

Max Range: 2.0996. Min Range: -2.0996

Max Act: 1.9237. Min Act: -0.1700

Data Index: 4778338 (Open Web Text)

Max Activating Token Index: 778

Text #18

Max Range: 2.0996. Min Range: -2.0996

Max Act: 1.8932. Min Act: -0.1700

Data Index: 188188 (Open Web Text)

Max Activating Token Index: 44

Text #19

Max Range: 2.0996. Min Range: -2.0996

Max Act: 1.8948. Min Act: -0.1700

Data Index: 5708704 (Open Web Text)

Max Activating Token Index: 203