Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5221 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0230. Min Range: -6.0230
Max Act: 6.0230. Min Act: -0.1700
Data Index: 1119094 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0230. Min Range: -6.0230
Max Act: 6.0230. Min Act: -0.1700
Data Index: 250142 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0230. Min Range: -6.0230
Max Act: 5.8980. Min Act: -0.1700
Data Index: 1090509 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0230. Min Range: -6.0230
Max Act: 5.8980. Min Act: -0.1700
Data Index: 8580745 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0230. Min Range: -6.0230
Max Act: 5.8355. Min Act: -0.1700
Data Index: 1080554 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0230. Min Range: -6.0230
Max Act: 5.8668. Min Act: -0.1700
Data Index: 2510932 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0230. Min Range: -6.0230
Max Act: 5.8355. Min Act: -0.1700
Data Index: 1088394 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0230. Min Range: -6.0230
Max Act: 5.7418. Min Act: -0.1700
Data Index: 250143 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0230. Min Range: -6.0230
Max Act: 5.7105. Min Act: -0.1700
Data Index: 2510930 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0230. Min Range: -6.0230
Max Act: 5.6793. Min Act: -0.1700
Data Index: 4047095 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0230. Min Range: -6.0230
Max Act: 5.6168. Min Act: -0.1700
Data Index: 2264515 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0230. Min Range: -6.0230
Max Act: 5.5855. Min Act: -0.1700
Data Index: 5475535 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0230. Min Range: -6.0230
Max Act: 5.6168. Min Act: -0.1700
Data Index: 1088395 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0230. Min Range: -6.0230
Max Act: 5.6168. Min Act: -0.1700
Data Index: 5552514 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0230. Min Range: -6.0230
Max Act: 5.5543. Min Act: -0.1700
Data Index: 5475534 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0230. Min Range: -6.0230
Max Act: 5.5230. Min Act: -0.1700
Data Index: 5475533 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0230. Min Range: -6.0230
Max Act: 5.5230. Min Act: -0.1700
Data Index: 5271369 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0230. Min Range: -6.0230
Max Act: 5.4605. Min Act: -0.1700
Data Index: 5475536 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0230. Min Range: -6.0230
Max Act: 5.4293. Min Act: -0.1700
Data Index: 8502616 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0230. Min Range: -6.0230
Max Act: 5.4293. Min Act: -0.1700
Data Index: 6438689 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19