Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3682 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.9288. Min Act: -0.1700
Data Index: 7224067 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.8350. Min Act: -0.1700
Data Index: 4271688 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.8350. Min Act: -0.1700
Data Index: 4142949 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.7413. Min Act: -0.1700
Data Index: 976560 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.7100. Min Act: -0.1700
Data Index: 14301 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.7100. Min Act: -0.1700
Data Index: 4943567 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.6788. Min Act: -0.1700
Data Index: 6910598 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.6788. Min Act: -0.1700
Data Index: 6923093 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.6788. Min Act: -0.1700
Data Index: 453438 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.6163. Min Act: -0.1700
Data Index: 6281400 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.6163. Min Act: -0.1700
Data Index: 8595450 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.6163. Min Act: -0.1700
Data Index: 940174 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.6475. Min Act: -0.1700
Data Index: 3928336 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.6163. Min Act: -0.1700
Data Index: 4935792 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.5850. Min Act: -0.1700
Data Index: 2672649 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.5850. Min Act: -0.1700
Data Index: 1746909 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.5538. Min Act: -0.1700
Data Index: 582929 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.5538. Min Act: -0.1700
Data Index: 1932503 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.5850. Min Act: -0.1700
Data Index: 1014850 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9288. Min Range: -6.9288
Max Act: 6.5225. Min Act: -0.1700
Data Index: 659214 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19