Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2420 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2577. Min Range: -6.2577
Max Act: 6.2577. Min Act: -0.1700
Data Index: 6955126 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2577. Min Range: -6.2577
Max Act: 6.2264. Min Act: -0.1700
Data Index: 5176850 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2577. Min Range: -6.2577
Max Act: 6.2264. Min Act: -0.1700
Data Index: 37837 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2577. Min Range: -6.2577
Max Act: 6.1952. Min Act: -0.1700
Data Index: 940054 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2577. Min Range: -6.2577
Max Act: 6.1952. Min Act: -0.1700
Data Index: 4328913 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2577. Min Range: -6.2577
Max Act: 6.1952. Min Act: -0.1700
Data Index: 1513380 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2577. Min Range: -6.2577
Max Act: 6.1639. Min Act: -0.1700
Data Index: 2845256 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2577. Min Range: -6.2577
Max Act: 6.1327. Min Act: -0.1700
Data Index: 1482604 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2577. Min Range: -6.2577
Max Act: 6.1327. Min Act: -0.1700
Data Index: 4402354 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2577. Min Range: -6.2577
Max Act: 6.1327. Min Act: -0.1700
Data Index: 3594283 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2577. Min Range: -6.2577
Max Act: 6.1014. Min Act: -0.1700
Data Index: 1620101 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2577. Min Range: -6.2577
Max Act: 6.1327. Min Act: -0.1700
Data Index: 3116764 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2577. Min Range: -6.2577
Max Act: 6.1014. Min Act: -0.1700
Data Index: 2250787 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2577. Min Range: -6.2577
Max Act: 6.0702. Min Act: -0.1700
Data Index: 7047009 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2577. Min Range: -6.2577
Max Act: 6.0389. Min Act: -0.1700
Data Index: 3009099 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2577. Min Range: -6.2577
Max Act: 6.0389. Min Act: -0.1700
Data Index: 6539533 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2577. Min Range: -6.2577
Max Act: 6.0389. Min Act: -0.1700
Data Index: 6164410 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2577. Min Range: -6.2577
Max Act: 6.0389. Min Act: -0.1700
Data Index: 5495311 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2577. Min Range: -6.2577
Max Act: 6.0077. Min Act: -0.1700
Data Index: 1740344 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2577. Min Range: -6.2577
Max Act: 6.0077. Min Act: -0.1700
Data Index: 1783315 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19