Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1280 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.9128. Min Act: -0.1700
Data Index: 2293525 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.7565. Min Act: -0.1700
Data Index: 7607819 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.6940. Min Act: -0.1700
Data Index: 883137 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.6940. Min Act: -0.1700
Data Index: 3715837 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.6940. Min Act: -0.1700
Data Index: 8762971 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.6628. Min Act: -0.1700
Data Index: 610960 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.6628. Min Act: -0.1700
Data Index: 5595319 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.6003. Min Act: -0.1700
Data Index: 7236960 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.6003. Min Act: -0.1700
Data Index: 4949063 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.6003. Min Act: -0.1700
Data Index: 6008006 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.6003. Min Act: -0.1700
Data Index: 2628083 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.6003. Min Act: -0.1700
Data Index: 4271499 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.6003. Min Act: -0.1700
Data Index: 3865540 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.5690. Min Act: -0.1700
Data Index: 1950646 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.5690. Min Act: -0.1700
Data Index: 4847619 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.5690. Min Act: -0.1700
Data Index: 957111 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.5690. Min Act: -0.1700
Data Index: 5359564 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.6003. Min Act: -0.1700
Data Index: 4791512 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.5378. Min Act: -0.1700
Data Index: 2467994 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.5378. Min Act: -0.1700
Data Index: 3245662 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19