Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1920. Min Range: -8.1920
Max Act: 8.1920. Min Act: -0.1700
Data Index: 6472335 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1920. Min Range: -8.1920
Max Act: 7.7545. Min Act: -0.1700
Data Index: 65260 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1920. Min Range: -8.1920
Max Act: 7.7545. Min Act: -0.1700
Data Index: 4968040 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1920. Min Range: -8.1920
Max Act: 7.5670. Min Act: -0.1700
Data Index: 3865165 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1920. Min Range: -8.1920
Max Act: 7.5670. Min Act: -0.1700
Data Index: 6410470 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1920. Min Range: -8.1920
Max Act: 7.5045. Min Act: -0.1700
Data Index: 6309599 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1920. Min Range: -8.1920
Max Act: 7.4733. Min Act: -0.1700
Data Index: 6481075 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1920. Min Range: -8.1920
Max Act: 7.4733. Min Act: -0.1700
Data Index: 5352362 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1920. Min Range: -8.1920
Max Act: 7.4733. Min Act: -0.1700
Data Index: 1597689 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1920. Min Range: -8.1920
Max Act: 7.4108. Min Act: -0.1700
Data Index: 158539 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1920. Min Range: -8.1920
Max Act: 7.4108. Min Act: -0.1700
Data Index: 4837325 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1920. Min Range: -8.1920
Max Act: 7.3483. Min Act: -0.1700
Data Index: 5160047 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1920. Min Range: -8.1920
Max Act: 7.3483. Min Act: -0.1700
Data Index: 1434221 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1920. Min Range: -8.1920
Max Act: 7.3170. Min Act: -0.1700
Data Index: 3100594 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1920. Min Range: -8.1920
Max Act: 7.2858. Min Act: -0.1700
Data Index: 1531697 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1920. Min Range: -8.1920
Max Act: 7.3170. Min Act: -0.1700
Data Index: 1789224 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1920. Min Range: -8.1920
Max Act: 7.3170. Min Act: -0.1700
Data Index: 883971 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1920. Min Range: -8.1920
Max Act: 7.3170. Min Act: -0.1700
Data Index: 785816 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1920. Min Range: -8.1920
Max Act: 7.3170. Min Act: -0.1700
Data Index: 2424451 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1920. Min Range: -8.1920
Max Act: 7.2545. Min Act: -0.1700
Data Index: 273831 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19