Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5109 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9384. Min Range: -6.9384
Max Act: 6.9384. Min Act: -0.1700
Data Index: 5653893 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9384. Min Range: -6.9384
Max Act: 6.8446. Min Act: -0.1700
Data Index: 5856970 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9384. Min Range: -6.9384
Max Act: 6.7196. Min Act: -0.1700
Data Index: 7753010 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9384. Min Range: -6.9384
Max Act: 6.5946. Min Act: -0.1700
Data Index: 7482392 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9384. Min Range: -6.9384
Max Act: 6.5321. Min Act: -0.1700
Data Index: 7404915 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9384. Min Range: -6.9384
Max Act: 6.5634. Min Act: -0.1700
Data Index: 1793124 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9384. Min Range: -6.9384
Max Act: 6.5009. Min Act: -0.1700
Data Index: 3142371 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9384. Min Range: -6.9384
Max Act: 6.5009. Min Act: -0.1700
Data Index: 4676919 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9384. Min Range: -6.9384
Max Act: 6.5009. Min Act: -0.1700
Data Index: 7753008 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9384. Min Range: -6.9384
Max Act: 6.4384. Min Act: -0.1700
Data Index: 7243187 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9384. Min Range: -6.9384
Max Act: 6.4696. Min Act: -0.1700
Data Index: 835911 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9384. Min Range: -6.9384
Max Act: 6.4696. Min Act: -0.1700
Data Index: 6197946 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9384. Min Range: -6.9384
Max Act: 6.4071. Min Act: -0.1700
Data Index: 7181890 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9384. Min Range: -6.9384
Max Act: 6.4071. Min Act: -0.1700
Data Index: 3185236 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9384. Min Range: -6.9384
Max Act: 6.3759. Min Act: -0.1700
Data Index: 357466 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9384. Min Range: -6.9384
Max Act: 6.3759. Min Act: -0.1700
Data Index: 4506837 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9384. Min Range: -6.9384
Max Act: 6.3446. Min Act: -0.1700
Data Index: 7753009 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9384. Min Range: -6.9384
Max Act: 6.3446. Min Act: -0.1700
Data Index: 743553 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9384. Min Range: -6.9384
Max Act: 6.3134. Min Act: -0.1700
Data Index: 4439540 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9384. Min Range: -6.9384
Max Act: 6.2509. Min Act: -0.1700
Data Index: 4200912 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19