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

Dataset: Open Web Text

Neuron 905 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: 1.9315. Min Range: -1.9315

Max Act: 1.9315. Min Act: -0.1700

Data Index: 7664625 (Open Web Text)

Max Activating Token Index: 265

Text #1

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.8945. Min Act: -0.1700

Data Index: 3524466 (Open Web Text)

Max Activating Token Index: 321

Text #2

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.8259. Min Act: -0.1700

Data Index: 3403454 (Open Web Text)

Max Activating Token Index: 266

Text #3

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.8428. Min Act: -0.1700

Data Index: 869515 (Open Web Text)

Max Activating Token Index: 801

Text #4

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.8443. Min Act: -0.1700

Data Index: 172037 (Open Web Text)

Max Activating Token Index: 636

Text #5

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.8193. Min Act: -0.1700

Data Index: 3053741 (Open Web Text)

Max Activating Token Index: 483

Text #6

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.8343. Min Act: -0.1700

Data Index: 5133261 (Open Web Text)

Max Activating Token Index: 270

Text #7

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.8364. Min Act: -0.1700

Data Index: 7467788 (Open Web Text)

Max Activating Token Index: 808

Text #8

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.8284. Min Act: -0.1700

Data Index: 4380397 (Open Web Text)

Max Activating Token Index: 176

Text #9

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.8270. Min Act: -0.1700

Data Index: 2948338 (Open Web Text)

Max Activating Token Index: 1017

Text #10

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.8030. Min Act: -0.1700

Data Index: 6431678 (Open Web Text)

Max Activating Token Index: 62

Text #11

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.8036. Min Act: -0.1700

Data Index: 7897693 (Open Web Text)

Max Activating Token Index: 161

Text #12

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.7948. Min Act: -0.1700

Data Index: 4276752 (Open Web Text)

Max Activating Token Index: 591

Text #13

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.7953. Min Act: -0.1700

Data Index: 6258706 (Open Web Text)

Max Activating Token Index: 648

Text #14

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.7861. Min Act: -0.1700

Data Index: 6782202 (Open Web Text)

Max Activating Token Index: 847

Text #15

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.7780. Min Act: -0.1700

Data Index: 3500544 (Open Web Text)

Max Activating Token Index: 456

Text #16

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.7885. Min Act: -0.1700

Data Index: 954245 (Open Web Text)

Max Activating Token Index: 611

Text #17

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.7784. Min Act: -0.1700

Data Index: 4525774 (Open Web Text)

Max Activating Token Index: 765

Text #18

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.7835. Min Act: -0.1700

Data Index: 1147934 (Open Web Text)

Max Activating Token Index: 639

Text #19

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.7758. Min Act: -0.1700

Data Index: 3259504 (Open Web Text)

Max Activating Token Index: 680