Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4285 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1004. Min Range: -4.1004
Max Act: 4.1004. Min Act: -0.1700
Data Index: 3334271 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1004. Min Range: -4.1004
Max Act: 4.1004. Min Act: -0.1700
Data Index: 6252314 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1004. Min Range: -4.1004
Max Act: 4.1004. Min Act: -0.1700
Data Index: 2820553 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1004. Min Range: -4.1004
Max Act: 4.0379. Min Act: -0.1700
Data Index: 6177823 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1004. Min Range: -4.1004
Max Act: 4.0067. Min Act: -0.1700
Data Index: 1658353 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1004. Min Range: -4.1004
Max Act: 3.9754. Min Act: -0.1700
Data Index: 3235779 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1004. Min Range: -4.1004
Max Act: 3.9441. Min Act: -0.1700
Data Index: 1696841 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1004. Min Range: -4.1004
Max Act: 3.9754. Min Act: -0.1700
Data Index: 4644103 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1004. Min Range: -4.1004
Max Act: 3.9754. Min Act: -0.1700
Data Index: 7636049 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1004. Min Range: -4.1004
Max Act: 3.9754. Min Act: -0.1700
Data Index: 3726180 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1004. Min Range: -4.1004
Max Act: 3.9754. Min Act: -0.1700
Data Index: 3043002 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1004. Min Range: -4.1004
Max Act: 3.9441. Min Act: -0.1700
Data Index: 2970119 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1004. Min Range: -4.1004
Max Act: 3.9441. Min Act: -0.1700
Data Index: 498574 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1004. Min Range: -4.1004
Max Act: 3.9441. Min Act: -0.1700
Data Index: 4464306 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1004. Min Range: -4.1004
Max Act: 3.9441. Min Act: -0.1700
Data Index: 6452130 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1004. Min Range: -4.1004
Max Act: 3.9441. Min Act: -0.1700
Data Index: 2993011 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1004. Min Range: -4.1004
Max Act: 3.9441. Min Act: -0.1700
Data Index: 3799114 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1004. Min Range: -4.1004
Max Act: 3.9441. Min Act: -0.1700
Data Index: 5181075 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1004. Min Range: -4.1004
Max Act: 3.9441. Min Act: -0.1700
Data Index: 5656583 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1004. Min Range: -4.1004
Max Act: 3.9129. Min Act: -0.1700
Data Index: 6226642 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19