Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3364 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1215. Min Range: -6.1215
Max Act: 6.1215. Min Act: -0.1454
Data Index: 681521 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1215. Min Range: -6.1215
Max Act: 6.0278. Min Act: -0.1699
Data Index: 681524 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1215. Min Range: -6.1215
Max Act: 5.9653. Min Act: -0.1699
Data Index: 6607212 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1215. Min Range: -6.1215
Max Act: 5.9340. Min Act: -0.1547
Data Index: 2404145 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1215. Min Range: -6.1215
Max Act: 5.9028. Min Act: -0.1693
Data Index: 2513097 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1215. Min Range: -6.1215
Max Act: 5.9028. Min Act: -0.1699
Data Index: 1031337 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1215. Min Range: -6.1215
Max Act: 5.8715. Min Act: -0.1698
Data Index: 681517 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1215. Min Range: -6.1215
Max Act: 5.8715. Min Act: -0.1673
Data Index: 2513096 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1215. Min Range: -6.1215
Max Act: 5.8403. Min Act: -0.1698
Data Index: 3398185 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1215. Min Range: -6.1215
Max Act: 5.8403. Min Act: -0.1598
Data Index: 2513098 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1215. Min Range: -6.1215
Max Act: 5.7778. Min Act: -0.1700
Data Index: 7668453 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1215. Min Range: -6.1215
Max Act: 5.7778. Min Act: -0.1697
Data Index: 3404678 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1215. Min Range: -6.1215
Max Act: 5.7465. Min Act: -0.1698
Data Index: 681520 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1215. Min Range: -6.1215
Max Act: 5.7465. Min Act: -0.1700
Data Index: 7438763 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1215. Min Range: -6.1215
Max Act: 5.7153. Min Act: -0.1698
Data Index: 3404679 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1215. Min Range: -6.1215
Max Act: 5.7153. Min Act: -0.1700
Data Index: 4950165 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1215. Min Range: -6.1215
Max Act: 5.7153. Min Act: -0.1700
Data Index: 3398186 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1215. Min Range: -6.1215
Max Act: 5.7153. Min Act: -0.1700
Data Index: 6953127 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1215. Min Range: -6.1215
Max Act: 5.6215. Min Act: -0.1671
Data Index: 681518 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1215. Min Range: -6.1215
Max Act: 5.6528. Min Act: -0.1700
Data Index: 3958404 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19