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

Dataset: Open Web Text

Neuron 1621 in Layer 4

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: 3.4144. Min Range: -3.4144

Max Act: 3.4064. Min Act: -0.1700

Data Index: 681054 (Open Web Text)

Max Activating Token Index: 469

Text #1

Max Range: 3.4144. Min Range: -3.4144

Max Act: 3.4144. Min Act: -0.1700

Data Index: 8110386 (Open Web Text)

Max Activating Token Index: 248

Text #2

Max Range: 3.4144. Min Range: -3.4144

Max Act: 3.4039. Min Act: -0.1700

Data Index: 6027954 (Open Web Text)

Max Activating Token Index: 378

Text #3

Max Range: 3.4144. Min Range: -3.4144

Max Act: 3.4120. Min Act: -0.1700

Data Index: 3757871 (Open Web Text)

Max Activating Token Index: 552

Text #4

Max Range: 3.4144. Min Range: -3.4144

Max Act: 3.4024. Min Act: -0.1700

Data Index: 7587161 (Open Web Text)

Max Activating Token Index: 17

Text #5

Max Range: 3.4144. Min Range: -3.4144

Max Act: 3.3955. Min Act: -0.1700

Data Index: 1528447 (Open Web Text)

Max Activating Token Index: 547

Text #6

Max Range: 3.4144. Min Range: -3.4144

Max Act: 3.3805. Min Act: -0.1700

Data Index: 523019 (Open Web Text)

Max Activating Token Index: 1004

Text #7

Max Range: 3.4144. Min Range: -3.4144

Max Act: 3.3729. Min Act: -0.1700

Data Index: 8491112 (Open Web Text)

Max Activating Token Index: 248

Text #8

Max Range: 3.4144. Min Range: -3.4144

Max Act: 3.3544. Min Act: -0.1700

Data Index: 984832 (Open Web Text)

Max Activating Token Index: 194

Text #9

Max Range: 3.4144. Min Range: -3.4144

Max Act: 3.4041. Min Act: -0.1700

Data Index: 5619488 (Open Web Text)

Max Activating Token Index: 730

Text #10

Max Range: 3.4144. Min Range: -3.4144

Max Act: 3.3404. Min Act: -0.1700

Data Index: 2818471 (Open Web Text)

Max Activating Token Index: 597

Text #11

Max Range: 3.4144. Min Range: -3.4144

Max Act: 3.3642. Min Act: -0.1700

Data Index: 431186 (Open Web Text)

Max Activating Token Index: 629

Text #12

Max Range: 3.4144. Min Range: -3.4144

Max Act: 3.3506. Min Act: -0.1700

Data Index: 6838826 (Open Web Text)

Max Activating Token Index: 93

Text #13

Max Range: 3.4144. Min Range: -3.4144

Max Act: 3.3356. Min Act: -0.1700

Data Index: 7130664 (Open Web Text)

Max Activating Token Index: 470

Text #14

Max Range: 3.4144. Min Range: -3.4144

Max Act: 3.3340. Min Act: -0.1700

Data Index: 3624208 (Open Web Text)

Max Activating Token Index: 72

Text #15

Max Range: 3.4144. Min Range: -3.4144

Max Act: 3.3379. Min Act: -0.1700

Data Index: 2071285 (Open Web Text)

Max Activating Token Index: 818

Text #16

Max Range: 3.4144. Min Range: -3.4144

Max Act: 3.3191. Min Act: -0.1700

Data Index: 7230397 (Open Web Text)

Max Activating Token Index: 883

Text #17

Max Range: 3.4144. Min Range: -3.4144

Max Act: 3.3361. Min Act: -0.1700

Data Index: 3589708 (Open Web Text)

Max Activating Token Index: 533

Text #18

Max Range: 3.4144. Min Range: -3.4144

Max Act: 3.3400. Min Act: -0.1700

Data Index: 147519 (Open Web Text)

Max Activating Token Index: 97

Text #19

Max Range: 3.4144. Min Range: -3.4144

Max Act: 3.3135. Min Act: -0.1700

Data Index: 4372937 (Open Web Text)

Max Activating Token Index: 788