Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 814 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3148. Min Range: -5.3148
Max Act: 5.3148. Min Act: -0.1700
Data Index: 93113 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3148. Min Range: -5.3148
Max Act: 5.1898. Min Act: -0.1700
Data Index: 8598048 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3148. Min Range: -5.3148
Max Act: 5.1898. Min Act: -0.1700
Data Index: 5192753 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3148. Min Range: -5.3148
Max Act: 5.1898. Min Act: -0.1700
Data Index: 4086993 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3148. Min Range: -5.3148
Max Act: 5.1898. Min Act: -0.1700
Data Index: 1426737 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3148. Min Range: -5.3148
Max Act: 5.1586. Min Act: -0.1700
Data Index: 1911300 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3148. Min Range: -5.3148
Max Act: 5.1273. Min Act: -0.1700
Data Index: 184372 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3148. Min Range: -5.3148
Max Act: 5.1273. Min Act: -0.1700
Data Index: 2625150 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3148. Min Range: -5.3148
Max Act: 5.1273. Min Act: -0.1700
Data Index: 6820794 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3148. Min Range: -5.3148
Max Act: 5.1273. Min Act: -0.1700
Data Index: 4762133 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3148. Min Range: -5.3148
Max Act: 5.0961. Min Act: -0.1700
Data Index: 6083916 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3148. Min Range: -5.3148
Max Act: 5.0961. Min Act: -0.1700
Data Index: 4660236 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3148. Min Range: -5.3148
Max Act: 5.0961. Min Act: -0.1700
Data Index: 1081461 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3148. Min Range: -5.3148
Max Act: 5.0961. Min Act: -0.1700
Data Index: 7040821 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3148. Min Range: -5.3148
Max Act: 5.1273. Min Act: -0.1700
Data Index: 3781438 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3148. Min Range: -5.3148
Max Act: 5.0648. Min Act: -0.1700
Data Index: 60549 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3148. Min Range: -5.3148
Max Act: 5.0648. Min Act: -0.1700
Data Index: 635038 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3148. Min Range: -5.3148
Max Act: 5.0648. Min Act: -0.1700
Data Index: 475005 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3148. Min Range: -5.3148
Max Act: 5.0648. Min Act: -0.1700
Data Index: 8533163 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3148. Min Range: -5.3148
Max Act: 5.0648. Min Act: -0.1700
Data Index: 2574428 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19