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

Dataset: Open Web Text

Neuron 1184 in Layer 3

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: 3.8385. Min Range: -3.8385

Max Act: 3.8385. Min Act: -0.1700

Data Index: 4459853 (Open Web Text)

Max Activating Token Index: 210

Text #1

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.7440. Min Act: -0.1700

Data Index: 2432608 (Open Web Text)

Max Activating Token Index: 288

Text #2

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.7486. Min Act: -0.1700

Data Index: 2078973 (Open Web Text)

Max Activating Token Index: 153

Text #3

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.6948. Min Act: -0.1700

Data Index: 6713214 (Open Web Text)

Max Activating Token Index: 194

Text #4

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.6594. Min Act: -0.1700

Data Index: 8035567 (Open Web Text)

Max Activating Token Index: 347

Text #5

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.6620. Min Act: -0.1700

Data Index: 5317551 (Open Web Text)

Max Activating Token Index: 439

Text #6

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.6696. Min Act: -0.1700

Data Index: 189835 (Open Web Text)

Max Activating Token Index: 246

Text #7

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.6207. Min Act: -0.1700

Data Index: 2331561 (Open Web Text)

Max Activating Token Index: 378

Text #8

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.6423. Min Act: -0.1700

Data Index: 1400471 (Open Web Text)

Max Activating Token Index: 563

Text #9

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.6443. Min Act: -0.1700

Data Index: 6628913 (Open Web Text)

Max Activating Token Index: 651

Text #10

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.6374. Min Act: -0.1700

Data Index: 7834907 (Open Web Text)

Max Activating Token Index: 717

Text #11

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.5978. Min Act: -0.1700

Data Index: 4084694 (Open Web Text)

Max Activating Token Index: 563

Text #12

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.6097. Min Act: -0.1700

Data Index: 5083076 (Open Web Text)

Max Activating Token Index: 296

Text #13

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.5970. Min Act: -0.1700

Data Index: 8621964 (Open Web Text)

Max Activating Token Index: 100

Text #14

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.6134. Min Act: -0.1700

Data Index: 7274594 (Open Web Text)

Max Activating Token Index: 200

Text #15

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.6253. Min Act: -0.1700

Data Index: 1106050 (Open Web Text)

Max Activating Token Index: 160

Text #16

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.5851. Min Act: -0.1700

Data Index: 6197842 (Open Web Text)

Max Activating Token Index: 259

Text #17

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.5772. Min Act: -0.1700

Data Index: 139803 (Open Web Text)

Max Activating Token Index: 483

Text #18

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.5567. Min Act: -0.1700

Data Index: 6958018 (Open Web Text)

Max Activating Token Index: 415

Text #19

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.5905. Min Act: -0.1700

Data Index: 7151552 (Open Web Text)

Max Activating Token Index: 170