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

Dataset: Open Web Text

Neuron 1590 in Layer 4

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: 4.3119. Min Range: -4.3119

Max Act: 4.3119. Min Act: -0.1700

Data Index: 4415595 (Open Web Text)

Max Activating Token Index: 55

Text #1

Max Range: 4.3119. Min Range: -4.3119

Max Act: 4.1009. Min Act: -0.1700

Data Index: 4821229 (Open Web Text)

Max Activating Token Index: 71

Text #2

Max Range: 4.3119. Min Range: -4.3119

Max Act: 4.1522. Min Act: -0.1700

Data Index: 3220060 (Open Web Text)

Max Activating Token Index: 356

Text #3

Max Range: 4.3119. Min Range: -4.3119

Max Act: 4.0681. Min Act: -0.1700

Data Index: 5318834 (Open Web Text)

Max Activating Token Index: 135

Text #4

Max Range: 4.3119. Min Range: -4.3119

Max Act: 4.0314. Min Act: -0.1700

Data Index: 2725358 (Open Web Text)

Max Activating Token Index: 62

Text #5

Max Range: 4.3119. Min Range: -4.3119

Max Act: 4.0398. Min Act: -0.1700

Data Index: 1950330 (Open Web Text)

Max Activating Token Index: 361

Text #6

Max Range: 4.3119. Min Range: -4.3119

Max Act: 3.9191. Min Act: -0.1700

Data Index: 4571675 (Open Web Text)

Max Activating Token Index: 691

Text #7

Max Range: 4.3119. Min Range: -4.3119

Max Act: 3.9450. Min Act: -0.1700

Data Index: 915027 (Open Web Text)

Max Activating Token Index: 740

Text #8

Max Range: 4.3119. Min Range: -4.3119

Max Act: 3.9301. Min Act: -0.1700

Data Index: 551411 (Open Web Text)

Max Activating Token Index: 634

Text #9

Max Range: 4.3119. Min Range: -4.3119

Max Act: 3.9034. Min Act: -0.1700

Data Index: 2855248 (Open Web Text)

Max Activating Token Index: 165

Text #10

Max Range: 4.3119. Min Range: -4.3119

Max Act: 3.9080. Min Act: -0.1700

Data Index: 5595610 (Open Web Text)

Max Activating Token Index: 226

Text #11

Max Range: 4.3119. Min Range: -4.3119

Max Act: 3.8602. Min Act: -0.1700

Data Index: 6918084 (Open Web Text)

Max Activating Token Index: 211

Text #12

Max Range: 4.3119. Min Range: -4.3119

Max Act: 3.8393. Min Act: -0.1700

Data Index: 3501974 (Open Web Text)

Max Activating Token Index: 961

Text #13

Max Range: 4.3119. Min Range: -4.3119

Max Act: 3.8208. Min Act: -0.1700

Data Index: 7148656 (Open Web Text)

Max Activating Token Index: 947

Text #14

Max Range: 4.3119. Min Range: -4.3119

Max Act: 3.8523. Min Act: -0.1700

Data Index: 3289399 (Open Web Text)

Max Activating Token Index: 419

Text #15

Max Range: 4.3119. Min Range: -4.3119

Max Act: 3.8447. Min Act: -0.1700

Data Index: 2455758 (Open Web Text)

Max Activating Token Index: 528

Text #16

Max Range: 4.3119. Min Range: -4.3119

Max Act: 3.7282. Min Act: -0.1700

Data Index: 4030187 (Open Web Text)

Max Activating Token Index: 60

Text #17

Max Range: 4.3119. Min Range: -4.3119

Max Act: 3.7225. Min Act: -0.1700

Data Index: 5432832 (Open Web Text)

Max Activating Token Index: 301

Text #18

Max Range: 4.3119. Min Range: -4.3119

Max Act: 3.6819. Min Act: -0.1700

Data Index: 3587097 (Open Web Text)

Max Activating Token Index: 64

Text #19

Max Range: 4.3119. Min Range: -4.3119

Max Act: 3.7399. Min Act: -0.1700

Data Index: 68643 (Open Web Text)

Max Activating Token Index: 875