Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3475 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8762. Min Range: -5.8762
Max Act: 5.8762. Min Act: -0.1700
Data Index: 8399562 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8762. Min Range: -5.8762
Max Act: 5.8449. Min Act: -0.1700
Data Index: 158838 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8762. Min Range: -5.8762
Max Act: 5.7824. Min Act: -0.1700
Data Index: 3854543 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8762. Min Range: -5.8762
Max Act: 5.7512. Min Act: -0.1700
Data Index: 6722098 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8762. Min Range: -5.8762
Max Act: 5.7512. Min Act: -0.1700
Data Index: 2805398 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8762. Min Range: -5.8762
Max Act: 5.7512. Min Act: -0.1700
Data Index: 8023507 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8762. Min Range: -5.8762
Max Act: 5.6887. Min Act: -0.1700
Data Index: 2575977 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8762. Min Range: -5.8762
Max Act: 5.7199. Min Act: -0.1700
Data Index: 8106027 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8762. Min Range: -5.8762
Max Act: 5.7199. Min Act: -0.1700
Data Index: 3525648 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8762. Min Range: -5.8762
Max Act: 5.7199. Min Act: -0.1700
Data Index: 5592728 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8762. Min Range: -5.8762
Max Act: 5.6887. Min Act: -0.1700
Data Index: 2116797 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8762. Min Range: -5.8762
Max Act: 5.6887. Min Act: -0.1700
Data Index: 3664970 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8762. Min Range: -5.8762
Max Act: 5.6574. Min Act: -0.1700
Data Index: 3300760 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8762. Min Range: -5.8762
Max Act: 5.6574. Min Act: -0.1700
Data Index: 6722099 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8762. Min Range: -5.8762
Max Act: 5.6574. Min Act: -0.1700
Data Index: 5106818 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8762. Min Range: -5.8762
Max Act: 5.6262. Min Act: -0.1700
Data Index: 5654159 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8762. Min Range: -5.8762
Max Act: 5.6262. Min Act: -0.1700
Data Index: 531185 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8762. Min Range: -5.8762
Max Act: 5.6262. Min Act: -0.1700
Data Index: 158836 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8762. Min Range: -5.8762
Max Act: 5.5949. Min Act: -0.1700
Data Index: 2143236 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8762. Min Range: -5.8762
Max Act: 5.5949. Min Act: -0.1700
Data Index: 6535565 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19