Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 415 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9132. Min Range: -6.9132
Max Act: 6.8507. Min Act: -0.1700
Data Index: 3881419 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9132. Min Range: -6.9132
Max Act: 6.9132. Min Act: -0.1700
Data Index: 6287145 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9132. Min Range: -6.9132
Max Act: 6.7882. Min Act: -0.1700
Data Index: 3063778 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9132. Min Range: -6.9132
Max Act: 6.7882. Min Act: -0.1700
Data Index: 5267631 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9132. Min Range: -6.9132
Max Act: 6.7882. Min Act: -0.1700
Data Index: 6381263 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9132. Min Range: -6.9132
Max Act: 6.7257. Min Act: -0.1700
Data Index: 2665867 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9132. Min Range: -6.9132
Max Act: 6.7257. Min Act: -0.1700
Data Index: 7585108 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9132. Min Range: -6.9132
Max Act: 6.7257. Min Act: -0.1700
Data Index: 7112385 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9132. Min Range: -6.9132
Max Act: 6.7257. Min Act: -0.1700
Data Index: 6539575 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9132. Min Range: -6.9132
Max Act: 6.7257. Min Act: -0.1700
Data Index: 5413118 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9132. Min Range: -6.9132
Max Act: 6.7257. Min Act: -0.1700
Data Index: 4899379 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9132. Min Range: -6.9132
Max Act: 6.7257. Min Act: -0.1700
Data Index: 6088826 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9132. Min Range: -6.9132
Max Act: 6.7257. Min Act: -0.1700
Data Index: 1009801 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9132. Min Range: -6.9132
Max Act: 6.6632. Min Act: -0.1700
Data Index: 426487 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9132. Min Range: -6.9132
Max Act: 6.6632. Min Act: -0.1700
Data Index: 5995778 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9132. Min Range: -6.9132
Max Act: 6.6632. Min Act: -0.1700
Data Index: 6456356 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9132. Min Range: -6.9132
Max Act: 6.6632. Min Act: -0.1700
Data Index: 5500417 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9132. Min Range: -6.9132
Max Act: 6.6632. Min Act: -0.1700
Data Index: 188642 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9132. Min Range: -6.9132
Max Act: 6.6632. Min Act: -0.1700
Data Index: 5500414 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9132. Min Range: -6.9132
Max Act: 6.6632. Min Act: -0.1700
Data Index: 188648 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19