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

Dataset: Open Web Text

Neuron 1119 in Layer 6

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: 3.4322. Min Range: -3.4322

Max Act: 3.4322. Min Act: -0.1700

Data Index: 1335004 (Open Web Text)

Max Activating Token Index: 690

Text #1

Max Range: 3.4322. Min Range: -3.4322

Max Act: 3.2842. Min Act: -0.1700

Data Index: 3361831 (Open Web Text)

Max Activating Token Index: 388

Text #2

Max Range: 3.4322. Min Range: -3.4322

Max Act: 3.2605. Min Act: -0.1700

Data Index: 105316 (Open Web Text)

Max Activating Token Index: 462

Text #3

Max Range: 3.4322. Min Range: -3.4322

Max Act: 3.2673. Min Act: -0.1700

Data Index: 7885036 (Open Web Text)

Max Activating Token Index: 670

Text #4

Max Range: 3.4322. Min Range: -3.4322

Max Act: 3.2474. Min Act: -0.1700

Data Index: 11800 (Open Web Text)

Max Activating Token Index: 91

Text #5

Max Range: 3.4322. Min Range: -3.4322

Max Act: 3.2440. Min Act: -0.1700

Data Index: 8709644 (Open Web Text)

Max Activating Token Index: 885

Text #6

Max Range: 3.4322. Min Range: -3.4322

Max Act: 3.2236. Min Act: -0.1700

Data Index: 1998800 (Open Web Text)

Max Activating Token Index: 786

Text #7

Max Range: 3.4322. Min Range: -3.4322

Max Act: 3.2367. Min Act: -0.1700

Data Index: 7938843 (Open Web Text)

Max Activating Token Index: 333

Text #8

Max Range: 3.4322. Min Range: -3.4322

Max Act: 3.2308. Min Act: -0.1700

Data Index: 5764902 (Open Web Text)

Max Activating Token Index: 318

Text #9

Max Range: 3.4322. Min Range: -3.4322

Max Act: 3.2339. Min Act: -0.1700

Data Index: 6473069 (Open Web Text)

Max Activating Token Index: 325

Text #10

Max Range: 3.4322. Min Range: -3.4322

Max Act: 3.2293. Min Act: -0.1700

Data Index: 1974905 (Open Web Text)

Max Activating Token Index: 640

Text #11

Max Range: 3.4322. Min Range: -3.4322

Max Act: 3.2203. Min Act: -0.1700

Data Index: 4922832 (Open Web Text)

Max Activating Token Index: 93

Text #12

Max Range: 3.4322. Min Range: -3.4322

Max Act: 3.2214. Min Act: -0.1700

Data Index: 8261663 (Open Web Text)

Max Activating Token Index: 784

Text #13

Max Range: 3.4322. Min Range: -3.4322

Max Act: 3.2287. Min Act: -0.1700

Data Index: 4526151 (Open Web Text)

Max Activating Token Index: 647

Text #14

Max Range: 3.4322. Min Range: -3.4322

Max Act: 3.2252. Min Act: -0.1700

Data Index: 8733251 (Open Web Text)

Max Activating Token Index: 770

Text #15

Max Range: 3.4322. Min Range: -3.4322

Max Act: 3.1958. Min Act: -0.1700

Data Index: 2680690 (Open Web Text)

Max Activating Token Index: 209

Text #16

Max Range: 3.4322. Min Range: -3.4322

Max Act: 3.2164. Min Act: -0.1700

Data Index: 6497237 (Open Web Text)

Max Activating Token Index: 696

Text #17

Max Range: 3.4322. Min Range: -3.4322

Max Act: 3.2073. Min Act: -0.1700

Data Index: 2441236 (Open Web Text)

Max Activating Token Index: 586

Text #18

Max Range: 3.4322. Min Range: -3.4322

Max Act: 3.1859. Min Act: -0.1700

Data Index: 6528094 (Open Web Text)

Max Activating Token Index: 816

Text #19

Max Range: 3.4322. Min Range: -3.4322

Max Act: 3.1891. Min Act: -0.1700

Data Index: 2750721 (Open Web Text)

Max Activating Token Index: 1000