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

Dataset: Open Web Text

Neuron 470 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: 3.7221. Min Range: -3.7221

Max Act: 3.7221. Min Act: -0.1700

Data Index: 911273 (Open Web Text)

Max Activating Token Index: 451

Text #1

Max Range: 3.7221. Min Range: -3.7221

Max Act: 3.6485. Min Act: -0.1700

Data Index: 8515334 (Open Web Text)

Max Activating Token Index: 527

Text #2

Max Range: 3.7221. Min Range: -3.7221

Max Act: 3.6634. Min Act: -0.1700

Data Index: 2775676 (Open Web Text)

Max Activating Token Index: 747

Text #3

Max Range: 3.7221. Min Range: -3.7221

Max Act: 3.6558. Min Act: -0.1700

Data Index: 7009250 (Open Web Text)

Max Activating Token Index: 154

Text #4

Max Range: 3.7221. Min Range: -3.7221

Max Act: 3.7051. Min Act: -0.1700

Data Index: 3204476 (Open Web Text)

Max Activating Token Index: 805

Text #5

Max Range: 3.7221. Min Range: -3.7221

Max Act: 3.6004. Min Act: -0.1700

Data Index: 7542812 (Open Web Text)

Max Activating Token Index: 684

Text #6

Max Range: 3.7221. Min Range: -3.7221

Max Act: 3.6289. Min Act: -0.1700

Data Index: 1244246 (Open Web Text)

Max Activating Token Index: 749

Text #7

Max Range: 3.7221. Min Range: -3.7221

Max Act: 3.5983. Min Act: -0.1700

Data Index: 8508604 (Open Web Text)

Max Activating Token Index: 268

Text #8

Max Range: 3.7221. Min Range: -3.7221

Max Act: 3.5752. Min Act: -0.1700

Data Index: 57052 (Open Web Text)

Max Activating Token Index: 297

Text #9

Max Range: 3.7221. Min Range: -3.7221

Max Act: 3.6152. Min Act: -0.1700

Data Index: 7682586 (Open Web Text)

Max Activating Token Index: 267

Text #10

Max Range: 3.7221. Min Range: -3.7221

Max Act: 3.5789. Min Act: -0.1700

Data Index: 2770241 (Open Web Text)

Max Activating Token Index: 700

Text #11

Max Range: 3.7221. Min Range: -3.7221

Max Act: 3.5629. Min Act: -0.1700

Data Index: 2777750 (Open Web Text)

Max Activating Token Index: 63

Text #12

Max Range: 3.7221. Min Range: -3.7221

Max Act: 3.5428. Min Act: -0.1700

Data Index: 5161591 (Open Web Text)

Max Activating Token Index: 60

Text #13

Max Range: 3.7221. Min Range: -3.7221

Max Act: 3.5535. Min Act: -0.1700

Data Index: 4745854 (Open Web Text)

Max Activating Token Index: 464

Text #14

Max Range: 3.7221. Min Range: -3.7221

Max Act: 3.5633. Min Act: -0.1700

Data Index: 5910430 (Open Web Text)

Max Activating Token Index: 204

Text #15

Max Range: 3.7221. Min Range: -3.7221

Max Act: 3.5715. Min Act: -0.1700

Data Index: 2743623 (Open Web Text)

Max Activating Token Index: 297

Text #16

Max Range: 3.7221. Min Range: -3.7221

Max Act: 3.5925. Min Act: -0.1700

Data Index: 3928401 (Open Web Text)

Max Activating Token Index: 322

Text #17

Max Range: 3.7221. Min Range: -3.7221

Max Act: 3.4869. Min Act: -0.1700

Data Index: 7128099 (Open Web Text)

Max Activating Token Index: 671

Text #18

Max Range: 3.7221. Min Range: -3.7221

Max Act: 3.5084. Min Act: -0.1700

Data Index: 3536883 (Open Web Text)

Max Activating Token Index: 373

Text #19

Max Range: 3.7221. Min Range: -3.7221

Max Act: 3.5449. Min Act: -0.1700

Data Index: 6897289 (Open Web Text)

Max Activating Token Index: 787