Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5043 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0008. Min Range: -6.0008
Max Act: 6.0008. Min Act: -0.1700
Data Index: 8293921 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0008. Min Range: -6.0008
Max Act: 5.9383. Min Act: -0.1700
Data Index: 648229 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0008. Min Range: -6.0008
Max Act: 5.8758. Min Act: -0.1700
Data Index: 4608496 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0008. Min Range: -6.0008
Max Act: 5.8445. Min Act: -0.1700
Data Index: 3271262 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0008. Min Range: -6.0008
Max Act: 5.8133. Min Act: -0.1700
Data Index: 7666675 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0008. Min Range: -6.0008
Max Act: 5.7820. Min Act: -0.1700
Data Index: 5373086 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0008. Min Range: -6.0008
Max Act: 5.7195. Min Act: -0.1700
Data Index: 7852318 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0008. Min Range: -6.0008
Max Act: 5.7195. Min Act: -0.1700
Data Index: 1579113 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0008. Min Range: -6.0008
Max Act: 5.6883. Min Act: -0.1700
Data Index: 838174 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0008. Min Range: -6.0008
Max Act: 5.6883. Min Act: -0.1700
Data Index: 45337 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0008. Min Range: -6.0008
Max Act: 5.6258. Min Act: -0.1700
Data Index: 771815 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0008. Min Range: -6.0008
Max Act: 5.6258. Min Act: -0.1700
Data Index: 104812 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0008. Min Range: -6.0008
Max Act: 5.6258. Min Act: -0.1700
Data Index: 8131206 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0008. Min Range: -6.0008
Max Act: 5.6258. Min Act: -0.1700
Data Index: 7332083 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0008. Min Range: -6.0008
Max Act: 5.6570. Min Act: -0.1700
Data Index: 6320535 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0008. Min Range: -6.0008
Max Act: 5.5633. Min Act: -0.1700
Data Index: 7140954 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0008. Min Range: -6.0008
Max Act: 5.5945. Min Act: -0.1700
Data Index: 459575 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0008. Min Range: -6.0008
Max Act: 5.5945. Min Act: -0.1700
Data Index: 3334533 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0008. Min Range: -6.0008
Max Act: 5.5945. Min Act: -0.1700
Data Index: 5817128 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0008. Min Range: -6.0008
Max Act: 5.5320. Min Act: -0.1700
Data Index: 2423064 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19