Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3257 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.3691. Min Act: -0.1700
Data Index: 2520241 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.2441. Min Act: -0.1700
Data Index: 5578391 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.0566. Min Act: -0.1700
Data Index: 1158987 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3691. Min Range: -5.3691
Max Act: 5.0253. Min Act: -0.1700
Data Index: 4613236 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3691. Min Range: -5.3691
Max Act: 4.9941. Min Act: -0.1700
Data Index: 5651783 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3691. Min Range: -5.3691
Max Act: 4.9628. Min Act: -0.1700
Data Index: 5527298 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3691. Min Range: -5.3691
Max Act: 4.9941. Min Act: -0.1700
Data Index: 4512437 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3691. Min Range: -5.3691
Max Act: 4.9316. Min Act: -0.1700
Data Index: 3746588 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3691. Min Range: -5.3691
Max Act: 4.9316. Min Act: -0.1700
Data Index: 5814262 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3691. Min Range: -5.3691
Max Act: 4.9316. Min Act: -0.1700
Data Index: 3817257 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3691. Min Range: -5.3691
Max Act: 4.8691. Min Act: -0.1700
Data Index: 2888184 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3691. Min Range: -5.3691
Max Act: 4.9003. Min Act: -0.1700
Data Index: 5989083 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3691. Min Range: -5.3691
Max Act: 4.9003. Min Act: -0.1700
Data Index: 7049722 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3691. Min Range: -5.3691
Max Act: 4.8691. Min Act: -0.1700
Data Index: 4248543 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3691. Min Range: -5.3691
Max Act: 4.8691. Min Act: -0.1700
Data Index: 8154141 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3691. Min Range: -5.3691
Max Act: 4.8691. Min Act: -0.1700
Data Index: 5768473 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3691. Min Range: -5.3691
Max Act: 4.8691. Min Act: -0.1700
Data Index: 4211895 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3691. Min Range: -5.3691
Max Act: 4.8691. Min Act: -0.1700
Data Index: 4036045 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3691. Min Range: -5.3691
Max Act: 4.8691. Min Act: -0.1700
Data Index: 2453150 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3691. Min Range: -5.3691
Max Act: 4.8691. Min Act: -0.1700
Data Index: 2640358 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19