Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5947 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0391. Min Range: -5.0391
Max Act: 5.0391. Min Act: -0.1700
Data Index: 7779813 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0391. Min Range: -5.0391
Max Act: 4.9141. Min Act: -0.1700
Data Index: 5185255 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0391. Min Range: -5.0391
Max Act: 4.8829. Min Act: -0.1700
Data Index: 5721706 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0391. Min Range: -5.0391
Max Act: 4.8516. Min Act: -0.1700
Data Index: 7569635 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0391. Min Range: -5.0391
Max Act: 4.8204. Min Act: -0.1700
Data Index: 2185294 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0391. Min Range: -5.0391
Max Act: 4.8204. Min Act: -0.1700
Data Index: 8308350 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0391. Min Range: -5.0391
Max Act: 4.8204. Min Act: -0.1700
Data Index: 185637 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0391. Min Range: -5.0391
Max Act: 4.8204. Min Act: -0.1700
Data Index: 4904586 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0391. Min Range: -5.0391
Max Act: 4.8204. Min Act: -0.1700
Data Index: 5498927 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0391. Min Range: -5.0391
Max Act: 4.8204. Min Act: -0.1700
Data Index: 5680977 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0391. Min Range: -5.0391
Max Act: 4.8204. Min Act: -0.1700
Data Index: 1959604 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0391. Min Range: -5.0391
Max Act: 4.7891. Min Act: -0.1700
Data Index: 944445 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0391. Min Range: -5.0391
Max Act: 4.8204. Min Act: -0.1700
Data Index: 1309125 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0391. Min Range: -5.0391
Max Act: 4.7891. Min Act: -0.1700
Data Index: 321558 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0391. Min Range: -5.0391
Max Act: 4.7891. Min Act: -0.1700
Data Index: 2992356 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0391. Min Range: -5.0391
Max Act: 4.7891. Min Act: -0.1700
Data Index: 7338199 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0391. Min Range: -5.0391
Max Act: 4.7891. Min Act: -0.1700
Data Index: 823968 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0391. Min Range: -5.0391
Max Act: 4.7891. Min Act: -0.1700
Data Index: 4134721 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0391. Min Range: -5.0391
Max Act: 4.7891. Min Act: -0.1700
Data Index: 2329739 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0391. Min Range: -5.0391
Max Act: 4.7579. Min Act: -0.1700
Data Index: 460754 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19