Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3960 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9597. Min Range: -1.9597
Max Act: 1.9597. Min Act: -0.1700
Data Index: 5422098 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9597. Min Range: -1.9597
Max Act: 1.9427. Min Act: -0.1700
Data Index: 4838316 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9597. Min Range: -1.9597
Max Act: 1.9086. Min Act: -0.1700
Data Index: 3297766 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9597. Min Range: -1.9597
Max Act: 1.9086. Min Act: -0.1700
Data Index: 93822 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9597. Min Range: -1.9597
Max Act: 1.9086. Min Act: -0.1700
Data Index: 3850920 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9597. Min Range: -1.9597
Max Act: 1.9086. Min Act: -0.1700
Data Index: 1840273 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9597. Min Range: -1.9597
Max Act: 1.8916. Min Act: -0.1700
Data Index: 2600253 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9597. Min Range: -1.9597
Max Act: 1.8916. Min Act: -0.1700
Data Index: 1707769 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9597. Min Range: -1.9597
Max Act: 1.8916. Min Act: -0.1700
Data Index: 6661081 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9597. Min Range: -1.9597
Max Act: 1.8916. Min Act: -0.1700
Data Index: 7067999 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9597. Min Range: -1.9597
Max Act: 1.8745. Min Act: -0.1700
Data Index: 4355877 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9597. Min Range: -1.9597
Max Act: 1.8745. Min Act: -0.1700
Data Index: 2600258 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9597. Min Range: -1.9597
Max Act: 1.8574. Min Act: -0.1700
Data Index: 5706711 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9597. Min Range: -1.9597
Max Act: 1.8574. Min Act: -0.1700
Data Index: 6424094 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9597. Min Range: -1.9597
Max Act: 1.8574. Min Act: -0.1700
Data Index: 2600256 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9597. Min Range: -1.9597
Max Act: 1.8574. Min Act: -0.1700
Data Index: 3524759 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9597. Min Range: -1.9597
Max Act: 1.8745. Min Act: -0.1700
Data Index: 4243888 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9597. Min Range: -1.9597
Max Act: 1.8574. Min Act: -0.1700
Data Index: 5192187 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9597. Min Range: -1.9597
Max Act: 1.8403. Min Act: -0.1700
Data Index: 4685562 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9597. Min Range: -1.9597
Max Act: 1.8403. Min Act: -0.1700
Data Index: 2600251 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19