Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3367 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8062. Min Range: -6.8062
Max Act: 6.8062. Min Act: -0.1700
Data Index: 3230821 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8062. Min Range: -6.8062
Max Act: 6.6500. Min Act: -0.1700
Data Index: 135528 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8062. Min Range: -6.8062
Max Act: 6.5875. Min Act: -0.1700
Data Index: 5132521 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8062. Min Range: -6.8062
Max Act: 6.5875. Min Act: -0.1700
Data Index: 995115 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8062. Min Range: -6.8062
Max Act: 6.5562. Min Act: -0.1700
Data Index: 60853 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8062. Min Range: -6.8062
Max Act: 6.5250. Min Act: -0.1700
Data Index: 8484642 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8062. Min Range: -6.8062
Max Act: 6.4937. Min Act: -0.1700
Data Index: 6621486 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8062. Min Range: -6.8062
Max Act: 6.5250. Min Act: -0.1700
Data Index: 220008 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8062. Min Range: -6.8062
Max Act: 6.4625. Min Act: -0.1700
Data Index: 7351424 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8062. Min Range: -6.8062
Max Act: 6.2750. Min Act: -0.1700
Data Index: 905691 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8062. Min Range: -6.8062
Max Act: 6.2437. Min Act: -0.1700
Data Index: 4494489 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8062. Min Range: -6.8062
Max Act: 6.2437. Min Act: -0.1700
Data Index: 4845859 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8062. Min Range: -6.8062
Max Act: 6.2750. Min Act: -0.1700
Data Index: 1070465 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8062. Min Range: -6.8062
Max Act: 6.2437. Min Act: -0.1700
Data Index: 4809610 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8062. Min Range: -6.8062
Max Act: 6.2125. Min Act: -0.1700
Data Index: 6080468 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8062. Min Range: -6.8062
Max Act: 6.1812. Min Act: -0.1700
Data Index: 8776062 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8062. Min Range: -6.8062
Max Act: 6.2125. Min Act: -0.1700
Data Index: 890744 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8062. Min Range: -6.8062
Max Act: 6.1812. Min Act: -0.1700
Data Index: 2584146 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8062. Min Range: -6.8062
Max Act: 6.1500. Min Act: -0.1700
Data Index: 2813728 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8062. Min Range: -6.8062
Max Act: 6.1500. Min Act: -0.1700
Data Index: 272132 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19