Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3074 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9667. Min Range: -5.9667
Max Act: 5.9667. Min Act: -0.1700
Data Index: 8227557 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9667. Min Range: -5.9667
Max Act: 5.8105. Min Act: -0.1700
Data Index: 2021863 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9667. Min Range: -5.9667
Max Act: 5.7792. Min Act: -0.1700
Data Index: 3735617 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9667. Min Range: -5.9667
Max Act: 5.7167. Min Act: -0.1700
Data Index: 1574985 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9667. Min Range: -5.9667
Max Act: 5.7167. Min Act: -0.1700
Data Index: 4612233 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9667. Min Range: -5.9667
Max Act: 5.6855. Min Act: -0.1700
Data Index: 870054 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9667. Min Range: -5.9667
Max Act: 5.6855. Min Act: -0.1700
Data Index: 3188219 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9667. Min Range: -5.9667
Max Act: 5.6855. Min Act: -0.1700
Data Index: 6799160 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9667. Min Range: -5.9667
Max Act: 5.6855. Min Act: -0.1700
Data Index: 815898 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9667. Min Range: -5.9667
Max Act: 5.6855. Min Act: -0.1700
Data Index: 8775202 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9667. Min Range: -5.9667
Max Act: 5.6230. Min Act: -0.1700
Data Index: 6422850 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9667. Min Range: -5.9667
Max Act: 5.6230. Min Act: -0.1700
Data Index: 2197000 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9667. Min Range: -5.9667
Max Act: 5.5917. Min Act: -0.1700
Data Index: 4190683 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9667. Min Range: -5.9667
Max Act: 5.6230. Min Act: -0.1700
Data Index: 3693267 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9667. Min Range: -5.9667
Max Act: 5.6542. Min Act: -0.1700
Data Index: 26522 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9667. Min Range: -5.9667
Max Act: 5.6230. Min Act: -0.1700
Data Index: 2983390 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9667. Min Range: -5.9667
Max Act: 5.5917. Min Act: -0.1700
Data Index: 4573505 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9667. Min Range: -5.9667
Max Act: 5.6230. Min Act: -0.1700
Data Index: 3000531 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9667. Min Range: -5.9667
Max Act: 5.5917. Min Act: -0.1700
Data Index: 7089644 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9667. Min Range: -5.9667
Max Act: 5.5917. Min Act: -0.1700
Data Index: 7702658 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19