Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3150 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0381. Min Range: -6.0381
Max Act: 6.0381. Min Act: -0.1700
Data Index: 5790244 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0381. Min Range: -6.0381
Max Act: 6.0381. Min Act: -0.1700
Data Index: 3903774 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.9756. Min Act: -0.1700
Data Index: 3164296 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0381. Min Range: -6.0381
Max Act: 6.0068. Min Act: -0.1700
Data Index: 1251408 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0381. Min Range: -6.0381
Max Act: 6.0068. Min Act: -0.1700
Data Index: 8148000 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.9756. Min Act: -0.1700
Data Index: 7981631 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.9756. Min Act: -0.1700
Data Index: 1106855 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.9756. Min Act: -0.1700
Data Index: 458770 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.9443. Min Act: -0.1700
Data Index: 3708461 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.9443. Min Act: -0.1700
Data Index: 3316133 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.8818. Min Act: -0.1700
Data Index: 3316128 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.9131. Min Act: -0.1700
Data Index: 5046221 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.9131. Min Act: -0.1700
Data Index: 1405856 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.9131. Min Act: -0.1700
Data Index: 3316124 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.9131. Min Act: -0.1700
Data Index: 7839192 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.9131. Min Act: -0.1700
Data Index: 320025 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.9131. Min Act: -0.1700
Data Index: 2218690 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.8818. Min Act: -0.1700
Data Index: 620329 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.8818. Min Act: -0.1700
Data Index: 997759 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.8818. Min Act: -0.1700
Data Index: 5302376 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19