Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7003. Min Range: -8.7003
Max Act: 8.7003. Min Act: -0.1700
Data Index: 7674639 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7003. Min Range: -8.7003
Max Act: 8.5753. Min Act: -0.1700
Data Index: 3388636 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7003. Min Range: -8.7003
Max Act: 8.5128. Min Act: -0.1700
Data Index: 8388907 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7003. Min Range: -8.7003
Max Act: 8.2628. Min Act: -0.1700
Data Index: 6434054 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7003. Min Range: -8.7003
Max Act: 8.2003. Min Act: -0.1700
Data Index: 2634420 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7003. Min Range: -8.7003
Max Act: 8.2628. Min Act: -0.1700
Data Index: 7807914 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7003. Min Range: -8.7003
Max Act: 8.0753. Min Act: -0.1700
Data Index: 3601617 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7003. Min Range: -8.7003
Max Act: 8.0753. Min Act: -0.1700
Data Index: 3240219 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7003. Min Range: -8.7003
Max Act: 8.0753. Min Act: -0.1700
Data Index: 564071 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7003. Min Range: -8.7003
Max Act: 8.0128. Min Act: -0.1700
Data Index: 7925741 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7003. Min Range: -8.7003
Max Act: 8.0753. Min Act: -0.1700
Data Index: 3850506 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7003. Min Range: -8.7003
Max Act: 7.9503. Min Act: -0.1700
Data Index: 2341158 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7003. Min Range: -8.7003
Max Act: 7.9503. Min Act: -0.1700
Data Index: 6047595 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7003. Min Range: -8.7003
Max Act: 7.8253. Min Act: -0.1700
Data Index: 3108012 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7003. Min Range: -8.7003
Max Act: 7.8253. Min Act: -0.1700
Data Index: 1103966 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7003. Min Range: -8.7003
Max Act: 7.8253. Min Act: -0.1700
Data Index: 6242871 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7003. Min Range: -8.7003
Max Act: 7.8253. Min Act: -0.1700
Data Index: 6538181 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7003. Min Range: -8.7003
Max Act: 7.8253. Min Act: -0.1700
Data Index: 5457427 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7003. Min Range: -8.7003
Max Act: 7.8253. Min Act: -0.1700
Data Index: 6470696 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7003. Min Range: -8.7003
Max Act: 7.8878. Min Act: -0.1700
Data Index: 6416592 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19