Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3341 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7265. Min Range: -5.7265
Max Act: 5.7265. Min Act: -0.1700
Data Index: 6358480 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7265. Min Range: -5.7265
Max Act: 5.4452. Min Act: -0.1700
Data Index: 2728089 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7265. Min Range: -5.7265
Max Act: 5.3827. Min Act: -0.1700
Data Index: 4668156 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7265. Min Range: -5.7265
Max Act: 5.1640. Min Act: -0.1700
Data Index: 2166318 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7265. Min Range: -5.7265
Max Act: 5.1327. Min Act: -0.1700
Data Index: 8008267 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7265. Min Range: -5.7265
Max Act: 5.0702. Min Act: -0.1700
Data Index: 6102486 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7265. Min Range: -5.7265
Max Act: 5.0390. Min Act: -0.1700
Data Index: 3745020 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7265. Min Range: -5.7265
Max Act: 5.0390. Min Act: -0.1700
Data Index: 48209 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7265. Min Range: -5.7265
Max Act: 5.0077. Min Act: -0.1700
Data Index: 8196577 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7265. Min Range: -5.7265
Max Act: 5.0077. Min Act: -0.1700
Data Index: 3755764 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7265. Min Range: -5.7265
Max Act: 5.0077. Min Act: -0.1700
Data Index: 4766749 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7265. Min Range: -5.7265
Max Act: 5.0077. Min Act: -0.1700
Data Index: 110107 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7265. Min Range: -5.7265
Max Act: 4.9765. Min Act: -0.1700
Data Index: 8531101 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7265. Min Range: -5.7265
Max Act: 4.9765. Min Act: -0.1700
Data Index: 5279624 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7265. Min Range: -5.7265
Max Act: 4.9452. Min Act: -0.1700
Data Index: 8412486 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7265. Min Range: -5.7265
Max Act: 4.9452. Min Act: -0.1700
Data Index: 1230488 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7265. Min Range: -5.7265
Max Act: 4.9452. Min Act: -0.1700
Data Index: 3650243 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7265. Min Range: -5.7265
Max Act: 4.9140. Min Act: -0.1700
Data Index: 1842379 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7265. Min Range: -5.7265
Max Act: 4.9452. Min Act: -0.1700
Data Index: 7473100 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7265. Min Range: -5.7265
Max Act: 4.8827. Min Act: -0.1700
Data Index: 1027709 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19