Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3588 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1089. Min Range: -6.1089
Max Act: 6.1089. Min Act: -0.1700
Data Index: 2158985 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1089. Min Range: -6.1089
Max Act: 6.0777. Min Act: -0.1700
Data Index: 7000662 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1089. Min Range: -6.1089
Max Act: 6.0152. Min Act: -0.1700
Data Index: 1506266 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1089. Min Range: -6.1089
Max Act: 6.0152. Min Act: -0.1700
Data Index: 1949368 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1089. Min Range: -6.1089
Max Act: 5.9527. Min Act: -0.1700
Data Index: 4731337 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1089. Min Range: -6.1089
Max Act: 5.9527. Min Act: -0.1700
Data Index: 5807504 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1089. Min Range: -6.1089
Max Act: 5.9214. Min Act: -0.1700
Data Index: 5162646 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1089. Min Range: -6.1089
Max Act: 5.9214. Min Act: -0.1700
Data Index: 7981193 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1089. Min Range: -6.1089
Max Act: 5.8902. Min Act: -0.1700
Data Index: 5968156 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1089. Min Range: -6.1089
Max Act: 5.9214. Min Act: -0.1700
Data Index: 4238000 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1089. Min Range: -6.1089
Max Act: 5.9214. Min Act: -0.1700
Data Index: 4439126 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1089. Min Range: -6.1089
Max Act: 5.9214. Min Act: -0.1700
Data Index: 7115347 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1089. Min Range: -6.1089
Max Act: 5.8902. Min Act: -0.1700
Data Index: 7769835 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1089. Min Range: -6.1089
Max Act: 5.8902. Min Act: -0.1700
Data Index: 6114187 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1089. Min Range: -6.1089
Max Act: 5.8902. Min Act: -0.1700
Data Index: 4438236 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1089. Min Range: -6.1089
Max Act: 5.8902. Min Act: -0.1700
Data Index: 5956469 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1089. Min Range: -6.1089
Max Act: 5.8589. Min Act: -0.1700
Data Index: 7368007 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1089. Min Range: -6.1089
Max Act: 5.8589. Min Act: -0.1700
Data Index: 4102011 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1089. Min Range: -6.1089
Max Act: 5.8277. Min Act: -0.1700
Data Index: 90725 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1089. Min Range: -6.1089
Max Act: 5.8589. Min Act: -0.1700
Data Index: 5914760 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19