Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2652 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1491. Min Range: -3.1491
Max Act: 3.1491. Min Act: -0.1700
Data Index: 1145463 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1491. Min Range: -3.1491
Max Act: 3.1333. Min Act: -0.1700
Data Index: 4400705 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1491. Min Range: -3.1491
Max Act: 3.1333. Min Act: -0.1700
Data Index: 5703938 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1491. Min Range: -3.1491
Max Act: 3.0387. Min Act: -0.1700
Data Index: 6658774 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1491. Min Range: -3.1491
Max Act: 3.0545. Min Act: -0.1700
Data Index: 1231425 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1491. Min Range: -3.1491
Max Act: 3.0545. Min Act: -0.1700
Data Index: 3105398 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1491. Min Range: -3.1491
Max Act: 3.0229. Min Act: -0.1700
Data Index: 2942094 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1491. Min Range: -3.1491
Max Act: 3.0229. Min Act: -0.1700
Data Index: 904369 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1491. Min Range: -3.1491
Max Act: 3.0071. Min Act: -0.1700
Data Index: 7849971 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1491. Min Range: -3.1491
Max Act: 2.9913. Min Act: -0.1700
Data Index: 3751570 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1491. Min Range: -3.1491
Max Act: 2.9755. Min Act: -0.1700
Data Index: 2485435 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1491. Min Range: -3.1491
Max Act: 2.9913. Min Act: -0.1700
Data Index: 6485476 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1491. Min Range: -3.1491
Max Act: 2.9913. Min Act: -0.1700
Data Index: 6760325 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1491. Min Range: -3.1491
Max Act: 2.9597. Min Act: -0.1700
Data Index: 8298111 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1491. Min Range: -3.1491
Max Act: 2.9597. Min Act: -0.1700
Data Index: 2551239 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1491. Min Range: -3.1491
Max Act: 2.9755. Min Act: -0.1700
Data Index: 1224318 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1491. Min Range: -3.1491
Max Act: 2.9755. Min Act: -0.1700
Data Index: 5277274 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1491. Min Range: -3.1491
Max Act: 2.9597. Min Act: -0.1700
Data Index: 5779048 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1491. Min Range: -3.1491
Max Act: 2.9755. Min Act: -0.1700
Data Index: 7805295 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1491. Min Range: -3.1491
Max Act: 2.9439. Min Act: -0.1700
Data Index: 5674686 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19