Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2786 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8720. Min Range: -5.8720
Max Act: 5.8720. Min Act: -0.1700
Data Index: 968684 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8720. Min Range: -5.8720
Max Act: 5.8720. Min Act: -0.1700
Data Index: 145351 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8720. Min Range: -5.8720
Max Act: 5.5283. Min Act: -0.1700
Data Index: 8157177 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8720. Min Range: -5.8720
Max Act: 5.5283. Min Act: -0.1700
Data Index: 2702643 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8720. Min Range: -5.8720
Max Act: 5.4970. Min Act: -0.1700
Data Index: 3598143 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8720. Min Range: -5.8720
Max Act: 5.4970. Min Act: -0.1700
Data Index: 4484094 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8720. Min Range: -5.8720
Max Act: 5.4345. Min Act: -0.1700
Data Index: 1353109 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8720. Min Range: -5.8720
Max Act: 5.4345. Min Act: -0.1700
Data Index: 5202471 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8720. Min Range: -5.8720
Max Act: 5.4345. Min Act: -0.1700
Data Index: 5643589 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8720. Min Range: -5.8720
Max Act: 5.4033. Min Act: -0.1700
Data Index: 4866499 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8720. Min Range: -5.8720
Max Act: 5.3720. Min Act: -0.1700
Data Index: 7934348 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8720. Min Range: -5.8720
Max Act: 5.3720. Min Act: -0.1700
Data Index: 3892199 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8720. Min Range: -5.8720
Max Act: 5.3720. Min Act: -0.1700
Data Index: 8065884 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8720. Min Range: -5.8720
Max Act: 5.3720. Min Act: -0.1700
Data Index: 8118697 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8720. Min Range: -5.8720
Max Act: 5.4033. Min Act: -0.1700
Data Index: 7588447 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8720. Min Range: -5.8720
Max Act: 5.3720. Min Act: -0.1700
Data Index: 7716308 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8720. Min Range: -5.8720
Max Act: 5.3408. Min Act: -0.1700
Data Index: 670921 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8720. Min Range: -5.8720
Max Act: 5.3095. Min Act: -0.1700
Data Index: 6425359 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8720. Min Range: -5.8720
Max Act: 5.3095. Min Act: -0.1700
Data Index: 4484064 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8720. Min Range: -5.8720
Max Act: 5.3095. Min Act: -0.1700
Data Index: 7842631 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19