Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3458 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3821. Min Range: -6.3821
Max Act: 6.3821. Min Act: -0.1700
Data Index: 6957111 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3821. Min Range: -6.3821
Max Act: 6.1946. Min Act: -0.1700
Data Index: 7018228 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3821. Min Range: -6.3821
Max Act: 6.0071. Min Act: -0.1700
Data Index: 2041533 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3821. Min Range: -6.3821
Max Act: 5.9759. Min Act: -0.1700
Data Index: 4217467 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3821. Min Range: -6.3821
Max Act: 5.9759. Min Act: -0.1700
Data Index: 2847749 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3821. Min Range: -6.3821
Max Act: 5.9446. Min Act: -0.1700
Data Index: 2111204 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3821. Min Range: -6.3821
Max Act: 5.8821. Min Act: -0.1700
Data Index: 6954441 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3821. Min Range: -6.3821
Max Act: 5.8821. Min Act: -0.1700
Data Index: 6393730 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3821. Min Range: -6.3821
Max Act: 5.8821. Min Act: -0.1700
Data Index: 300394 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3821. Min Range: -6.3821
Max Act: 5.8821. Min Act: -0.1700
Data Index: 4682093 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3821. Min Range: -6.3821
Max Act: 5.8196. Min Act: -0.1700
Data Index: 7642913 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3821. Min Range: -6.3821
Max Act: 5.8196. Min Act: -0.1700
Data Index: 2650282 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3821. Min Range: -6.3821
Max Act: 5.8196. Min Act: -0.1700
Data Index: 8179949 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3821. Min Range: -6.3821
Max Act: 5.7884. Min Act: -0.1700
Data Index: 5757548 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3821. Min Range: -6.3821
Max Act: 5.7571. Min Act: -0.1700
Data Index: 3954252 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3821. Min Range: -6.3821
Max Act: 5.7571. Min Act: -0.1700
Data Index: 2426482 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3821. Min Range: -6.3821
Max Act: 5.7259. Min Act: -0.1700
Data Index: 2345401 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3821. Min Range: -6.3821
Max Act: 5.6946. Min Act: -0.1700
Data Index: 4886613 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3821. Min Range: -6.3821
Max Act: 5.6946. Min Act: -0.1700
Data Index: 5436764 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3821. Min Range: -6.3821
Max Act: 5.6946. Min Act: -0.1700
Data Index: 3483965 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19