Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5825 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9700. Min Range: -5.9700
Max Act: 5.9700. Min Act: -0.1700
Data Index: 5081656 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9700. Min Range: -5.9700
Max Act: 5.9075. Min Act: -0.1700
Data Index: 8275641 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9700. Min Range: -5.9700
Max Act: 5.9075. Min Act: -0.1700
Data Index: 3791912 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9700. Min Range: -5.9700
Max Act: 5.8762. Min Act: -0.1700
Data Index: 3482072 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9700. Min Range: -5.9700
Max Act: 5.8450. Min Act: -0.1700
Data Index: 8605637 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9700. Min Range: -5.9700
Max Act: 5.8450. Min Act: -0.1700
Data Index: 8281407 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9700. Min Range: -5.9700
Max Act: 5.8450. Min Act: -0.1700
Data Index: 4577513 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9700. Min Range: -5.9700
Max Act: 5.8137. Min Act: -0.1700
Data Index: 2441035 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9700. Min Range: -5.9700
Max Act: 5.7825. Min Act: -0.1700
Data Index: 8407839 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9700. Min Range: -5.9700
Max Act: 5.7512. Min Act: -0.1700
Data Index: 2716497 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9700. Min Range: -5.9700
Max Act: 5.7512. Min Act: -0.1700
Data Index: 1765064 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9700. Min Range: -5.9700
Max Act: 5.6887. Min Act: -0.1700
Data Index: 2095876 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9700. Min Range: -5.9700
Max Act: 5.6887. Min Act: -0.1700
Data Index: 1188496 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9700. Min Range: -5.9700
Max Act: 5.6887. Min Act: -0.1700
Data Index: 1242634 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9700. Min Range: -5.9700
Max Act: 5.6575. Min Act: -0.1700
Data Index: 338505 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9700. Min Range: -5.9700
Max Act: 5.6575. Min Act: -0.1700
Data Index: 4421675 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9700. Min Range: -5.9700
Max Act: 5.6575. Min Act: -0.1700
Data Index: 6592346 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9700. Min Range: -5.9700
Max Act: 5.6575. Min Act: -0.1700
Data Index: 7850566 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9700. Min Range: -5.9700
Max Act: 5.6262. Min Act: -0.1700
Data Index: 7802451 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9700. Min Range: -5.9700
Max Act: 5.6262. Min Act: -0.1700
Data Index: 820322 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19