Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4214 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4123. Min Range: -7.4123
Max Act: 7.4123. Min Act: -0.1700
Data Index: 4104076 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4123. Min Range: -7.4123
Max Act: 6.8811. Min Act: -0.1700
Data Index: 1451754 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4123. Min Range: -7.4123
Max Act: 6.8498. Min Act: -0.1700
Data Index: 2330394 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4123. Min Range: -7.4123
Max Act: 6.7873. Min Act: -0.1700
Data Index: 245820 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4123. Min Range: -7.4123
Max Act: 6.6623. Min Act: -0.1700
Data Index: 2477889 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4123. Min Range: -7.4123
Max Act: 6.5998. Min Act: -0.1700
Data Index: 3764820 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4123. Min Range: -7.4123
Max Act: 6.5061. Min Act: -0.1700
Data Index: 1322452 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4123. Min Range: -7.4123
Max Act: 6.4748. Min Act: -0.1700
Data Index: 1291870 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4123. Min Range: -7.4123
Max Act: 6.4436. Min Act: -0.1700
Data Index: 4016156 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4123. Min Range: -7.4123
Max Act: 6.4436. Min Act: -0.1700
Data Index: 7126913 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4123. Min Range: -7.4123
Max Act: 6.3811. Min Act: -0.1700
Data Index: 6991641 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4123. Min Range: -7.4123
Max Act: 6.3811. Min Act: -0.1700
Data Index: 7810907 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4123. Min Range: -7.4123
Max Act: 6.3811. Min Act: -0.1700
Data Index: 5867855 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4123. Min Range: -7.4123
Max Act: 6.3811. Min Act: -0.1700
Data Index: 4751443 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4123. Min Range: -7.4123
Max Act: 6.3498. Min Act: -0.1700
Data Index: 7159750 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4123. Min Range: -7.4123
Max Act: 6.3186. Min Act: -0.1700
Data Index: 2330395 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4123. Min Range: -7.4123
Max Act: 6.3186. Min Act: -0.1700
Data Index: 6527169 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4123. Min Range: -7.4123
Max Act: 6.3186. Min Act: -0.1700
Data Index: 5801838 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4123. Min Range: -7.4123
Max Act: 6.2873. Min Act: -0.1700
Data Index: 4878813 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4123. Min Range: -7.4123
Max Act: 6.2873. Min Act: -0.1700
Data Index: 7226920 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19