Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 72 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4859. Min Range: -6.4859
Max Act: 6.4859. Min Act: -0.1700
Data Index: 8345436 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4859. Min Range: -6.4859
Max Act: 6.3922. Min Act: -0.1700
Data Index: 1904708 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4859. Min Range: -6.4859
Max Act: 6.2672. Min Act: -0.1700
Data Index: 7060163 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4859. Min Range: -6.4859
Max Act: 6.1422. Min Act: -0.1700
Data Index: 2319849 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4859. Min Range: -6.4859
Max Act: 6.1109. Min Act: -0.1700
Data Index: 6513283 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4859. Min Range: -6.4859
Max Act: 6.0797. Min Act: -0.1700
Data Index: 7522772 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4859. Min Range: -6.4859
Max Act: 6.1109. Min Act: -0.1700
Data Index: 4439038 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4859. Min Range: -6.4859
Max Act: 6.0797. Min Act: -0.1700
Data Index: 6450319 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4859. Min Range: -6.4859
Max Act: 6.0797. Min Act: -0.1700
Data Index: 5575812 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4859. Min Range: -6.4859
Max Act: 6.0797. Min Act: -0.1700
Data Index: 1157709 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4859. Min Range: -6.4859
Max Act: 6.0484. Min Act: -0.1700
Data Index: 477722 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4859. Min Range: -6.4859
Max Act: 6.0172. Min Act: -0.1700
Data Index: 8777125 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4859. Min Range: -6.4859
Max Act: 6.0172. Min Act: -0.1700
Data Index: 2175062 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4859. Min Range: -6.4859
Max Act: 6.0172. Min Act: -0.1700
Data Index: 7766645 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4859. Min Range: -6.4859
Max Act: 6.0172. Min Act: -0.1700
Data Index: 4583990 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4859. Min Range: -6.4859
Max Act: 5.9859. Min Act: -0.1700
Data Index: 135953 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4859. Min Range: -6.4859
Max Act: 5.9859. Min Act: -0.1700
Data Index: 8009810 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4859. Min Range: -6.4859
Max Act: 5.9859. Min Act: -0.1700
Data Index: 3879735 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4859. Min Range: -6.4859
Max Act: 6.0172. Min Act: -0.1700
Data Index: 8279790 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4859. Min Range: -6.4859
Max Act: 5.9547. Min Act: -0.1700
Data Index: 4191475 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19