Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2281 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1591. Min Range: -3.1591
Max Act: 3.1591. Min Act: -0.1700
Data Index: 1749188 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1591. Min Range: -3.1591
Max Act: 3.1434. Min Act: -0.1700
Data Index: 3592318 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1591. Min Range: -3.1591
Max Act: 3.0961. Min Act: -0.1700
Data Index: 2832972 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1591. Min Range: -3.1591
Max Act: 3.0803. Min Act: -0.1700
Data Index: 4865304 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1591. Min Range: -3.1591
Max Act: 3.0803. Min Act: -0.1700
Data Index: 3838297 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1591. Min Range: -3.1591
Max Act: 3.0646. Min Act: -0.1700
Data Index: 660933 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1591. Min Range: -3.1591
Max Act: 3.0488. Min Act: -0.1700
Data Index: 819942 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1591. Min Range: -3.1591
Max Act: 3.0330. Min Act: -0.1700
Data Index: 4213155 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1591. Min Range: -3.1591
Max Act: 3.0330. Min Act: -0.1700
Data Index: 2125990 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1591. Min Range: -3.1591
Max Act: 3.0014. Min Act: -0.1700
Data Index: 4106134 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1591. Min Range: -3.1591
Max Act: 3.0172. Min Act: -0.1700
Data Index: 1391810 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1591. Min Range: -3.1591
Max Act: 3.0014. Min Act: -0.1700
Data Index: 1768349 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1591. Min Range: -3.1591
Max Act: 3.0014. Min Act: -0.1700
Data Index: 8489248 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1591. Min Range: -3.1591
Max Act: 3.0172. Min Act: -0.1700
Data Index: 1717762 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1591. Min Range: -3.1591
Max Act: 3.0172. Min Act: -0.1700
Data Index: 4120788 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1591. Min Range: -3.1591
Max Act: 2.9698. Min Act: -0.1700
Data Index: 3705776 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1591. Min Range: -3.1591
Max Act: 2.9698. Min Act: -0.1700
Data Index: 1805921 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1591. Min Range: -3.1591
Max Act: 2.9856. Min Act: -0.1700
Data Index: 5982894 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1591. Min Range: -3.1591
Max Act: 2.9698. Min Act: -0.1700
Data Index: 6313391 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1591. Min Range: -3.1591
Max Act: 2.9698. Min Act: -0.1700
Data Index: 8448009 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19