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

Dataset: Open Web Text

Neuron 2657 in Layer 5

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: 4.6249. Min Range: -4.6249

Max Act: 4.6249. Min Act: -0.1700

Data Index: 1209637 (Open Web Text)

Max Activating Token Index: 898

Text #1

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.4882. Min Act: -0.1700

Data Index: 4343263 (Open Web Text)

Max Activating Token Index: 361

Text #2

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.4846. Min Act: -0.1700

Data Index: 2423543 (Open Web Text)

Max Activating Token Index: 619

Text #3

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.4814. Min Act: -0.1700

Data Index: 6832529 (Open Web Text)

Max Activating Token Index: 124

Text #4

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.4496. Min Act: -0.1700

Data Index: 1624471 (Open Web Text)

Max Activating Token Index: 755

Text #5

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.4382. Min Act: -0.1700

Data Index: 2400718 (Open Web Text)

Max Activating Token Index: 630

Text #6

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.4461. Min Act: -0.1700

Data Index: 1119668 (Open Web Text)

Max Activating Token Index: 247

Text #7

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.4087. Min Act: -0.1700

Data Index: 304043 (Open Web Text)

Max Activating Token Index: 545

Text #8

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.3790. Min Act: -0.1700

Data Index: 7087376 (Open Web Text)

Max Activating Token Index: 548

Text #9

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.3927. Min Act: -0.1700

Data Index: 5138456 (Open Web Text)

Max Activating Token Index: 464

Text #10

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.4018. Min Act: -0.1700

Data Index: 7916731 (Open Web Text)

Max Activating Token Index: 269

Text #11

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.3877. Min Act: -0.1700

Data Index: 6492123 (Open Web Text)

Max Activating Token Index: 691

Text #12

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.3759. Min Act: -0.1700

Data Index: 2659936 (Open Web Text)

Max Activating Token Index: 927

Text #13

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.4098. Min Act: -0.1700

Data Index: 1898761 (Open Web Text)

Max Activating Token Index: 774

Text #14

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.3969. Min Act: -0.1700

Data Index: 3215347 (Open Web Text)

Max Activating Token Index: 743

Text #15

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.4083. Min Act: -0.1700

Data Index: 7246537 (Open Web Text)

Max Activating Token Index: 514

Text #16

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.3464. Min Act: -0.1700

Data Index: 375047 (Open Web Text)

Max Activating Token Index: 134

Text #17

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.3335. Min Act: -0.1700

Data Index: 5119880 (Open Web Text)

Max Activating Token Index: 681

Text #18

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.3485. Min Act: -0.1700

Data Index: 2122065 (Open Web Text)

Max Activating Token Index: 119

Text #19

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.3703. Min Act: -0.1700

Data Index: 3198879 (Open Web Text)

Max Activating Token Index: 165