Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 972 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0521. Min Range: -6.0521
Max Act: 6.0521. Min Act: -0.1700
Data Index: 213008 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0521. Min Range: -6.0521
Max Act: 5.8334. Min Act: -0.1700
Data Index: 1104929 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0521. Min Range: -6.0521
Max Act: 5.8021. Min Act: -0.1700
Data Index: 680404 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0521. Min Range: -6.0521
Max Act: 5.8021. Min Act: -0.1700
Data Index: 4428015 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0521. Min Range: -6.0521
Max Act: 5.8021. Min Act: -0.1700
Data Index: 1690661 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0521. Min Range: -6.0521
Max Act: 5.7396. Min Act: -0.1700
Data Index: 1708731 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0521. Min Range: -6.0521
Max Act: 5.7084. Min Act: -0.1700
Data Index: 5787024 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0521. Min Range: -6.0521
Max Act: 5.6771. Min Act: -0.1700
Data Index: 42525 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0521. Min Range: -6.0521
Max Act: 5.6771. Min Act: -0.1700
Data Index: 8055547 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0521. Min Range: -6.0521
Max Act: 5.6459. Min Act: -0.1700
Data Index: 7336406 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0521. Min Range: -6.0521
Max Act: 5.6146. Min Act: -0.1700
Data Index: 6747035 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0521. Min Range: -6.0521
Max Act: 5.6459. Min Act: -0.1700
Data Index: 4416735 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0521. Min Range: -6.0521
Max Act: 5.6459. Min Act: -0.1700
Data Index: 2451181 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0521. Min Range: -6.0521
Max Act: 5.6146. Min Act: -0.1700
Data Index: 5364164 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0521. Min Range: -6.0521
Max Act: 5.6146. Min Act: -0.1700
Data Index: 4330764 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0521. Min Range: -6.0521
Max Act: 5.6459. Min Act: -0.1700
Data Index: 4293280 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0521. Min Range: -6.0521
Max Act: 5.5834. Min Act: -0.1700
Data Index: 7154643 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0521. Min Range: -6.0521
Max Act: 5.5834. Min Act: -0.1700
Data Index: 7167371 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0521. Min Range: -6.0521
Max Act: 5.5834. Min Act: -0.1700
Data Index: 4166858 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0521. Min Range: -6.0521
Max Act: 5.5834. Min Act: -0.1700
Data Index: 3498867 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19