Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3404 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.6134. Min Act: -0.1700
Data Index: 3624329 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.5509. Min Act: -0.1700
Data Index: 726024 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.5509. Min Act: -0.1700
Data Index: 1005578 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.5509. Min Act: -0.1700
Data Index: 5863469 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.5196. Min Act: -0.1700
Data Index: 3111845 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.4571. Min Act: -0.1700
Data Index: 897931 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.4884. Min Act: -0.1700
Data Index: 1221348 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.4571. Min Act: -0.1700
Data Index: 8173165 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.4259. Min Act: -0.1700
Data Index: 7834822 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.4259. Min Act: -0.1700
Data Index: 5496961 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.3946. Min Act: -0.1700
Data Index: 2176123 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.4259. Min Act: -0.1700
Data Index: 8231170 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.3946. Min Act: -0.1700
Data Index: 6963558 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.3634. Min Act: -0.1700
Data Index: 567309 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.3946. Min Act: -0.1700
Data Index: 5662739 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.4259. Min Act: -0.1700
Data Index: 5559774 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.3946. Min Act: -0.1700
Data Index: 3103155 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.3946. Min Act: -0.1700
Data Index: 2319326 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.3946. Min Act: -0.1700
Data Index: 212383 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.3946. Min Act: -0.1700
Data Index: 1037130 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19