Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 90 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2806. Min Range: -5.2806
Max Act: 5.2806. Min Act: -0.1700
Data Index: 3733099 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2806. Min Range: -5.2806
Max Act: 5.1556. Min Act: -0.1700
Data Index: 8802420 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2806. Min Range: -5.2806
Max Act: 5.0619. Min Act: -0.1700
Data Index: 6026851 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2806. Min Range: -5.2806
Max Act: 4.9369. Min Act: -0.1700
Data Index: 2666473 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2806. Min Range: -5.2806
Max Act: 4.9056. Min Act: -0.1700
Data Index: 5190681 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2806. Min Range: -5.2806
Max Act: 4.8744. Min Act: -0.1700
Data Index: 4593788 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2806. Min Range: -5.2806
Max Act: 4.8744. Min Act: -0.1700
Data Index: 6031010 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2806. Min Range: -5.2806
Max Act: 4.8431. Min Act: -0.1700
Data Index: 8802418 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2806. Min Range: -5.2806
Max Act: 4.8431. Min Act: -0.1700
Data Index: 7293044 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2806. Min Range: -5.2806
Max Act: 4.8744. Min Act: -0.1700
Data Index: 6026852 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2806. Min Range: -5.2806
Max Act: 4.7494. Min Act: -0.1700
Data Index: 4282769 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2806. Min Range: -5.2806
Max Act: 4.7806. Min Act: -0.1700
Data Index: 1356155 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2806. Min Range: -5.2806
Max Act: 4.7806. Min Act: -0.1700
Data Index: 6413139 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2806. Min Range: -5.2806
Max Act: 4.7806. Min Act: -0.1700
Data Index: 5375279 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2806. Min Range: -5.2806
Max Act: 4.7806. Min Act: -0.1700
Data Index: 7512613 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2806. Min Range: -5.2806
Max Act: 4.7806. Min Act: -0.1700
Data Index: 5368482 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2806. Min Range: -5.2806
Max Act: 4.7494. Min Act: -0.1700
Data Index: 8190197 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2806. Min Range: -5.2806
Max Act: 4.7181. Min Act: -0.1700
Data Index: 221261 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2806. Min Range: -5.2806
Max Act: 4.6869. Min Act: -0.1700
Data Index: 1079158 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2806. Min Range: -5.2806
Max Act: 4.6869. Min Act: -0.1700
Data Index: 3394970 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19