Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7589. Min Range: -5.7589
Max Act: 5.7589. Min Act: -0.1700
Data Index: 5158439 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7589. Min Range: -5.7589
Max Act: 5.6026. Min Act: -0.1700
Data Index: 808945 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7589. Min Range: -5.7589
Max Act: 5.5089. Min Act: -0.1700
Data Index: 2182709 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7589. Min Range: -5.7589
Max Act: 5.5401. Min Act: -0.1700
Data Index: 802914 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7589. Min Range: -5.7589
Max Act: 5.5089. Min Act: -0.1700
Data Index: 7630886 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7589. Min Range: -5.7589
Max Act: 5.5089. Min Act: -0.1700
Data Index: 6177356 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7589. Min Range: -5.7589
Max Act: 5.4776. Min Act: -0.1700
Data Index: 6671810 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7589. Min Range: -5.7589
Max Act: 5.4776. Min Act: -0.1700
Data Index: 1987510 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7589. Min Range: -5.7589
Max Act: 5.4776. Min Act: -0.1700
Data Index: 3801065 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7589. Min Range: -5.7589
Max Act: 5.4464. Min Act: -0.1700
Data Index: 6026936 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7589. Min Range: -5.7589
Max Act: 5.4464. Min Act: -0.1700
Data Index: 3039788 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7589. Min Range: -5.7589
Max Act: 5.4464. Min Act: -0.1700
Data Index: 3538767 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7589. Min Range: -5.7589
Max Act: 5.4464. Min Act: -0.1700
Data Index: 2182708 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7589. Min Range: -5.7589
Max Act: 5.4464. Min Act: -0.1700
Data Index: 460261 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7589. Min Range: -5.7589
Max Act: 5.4464. Min Act: -0.1700
Data Index: 1049347 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7589. Min Range: -5.7589
Max Act: 5.4464. Min Act: -0.1700
Data Index: 4197890 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7589. Min Range: -5.7589
Max Act: 5.4464. Min Act: -0.1700
Data Index: 4125126 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7589. Min Range: -5.7589
Max Act: 5.4464. Min Act: -0.1700
Data Index: 6312890 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7589. Min Range: -5.7589
Max Act: 5.4151. Min Act: -0.1700
Data Index: 948141 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7589. Min Range: -5.7589
Max Act: 5.4151. Min Act: -0.1700
Data Index: 855762 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19