Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1221 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 11.8169. Min Range: -11.8169
Max Act: 11.8169. Min Act: -0.1700
Data Index: 7517397 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8169. Min Range: -11.8169
Max Act: 11.0044. Min Act: -0.1700
Data Index: 2932579 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8169. Min Range: -11.8169
Max Act: 11.0044. Min Act: -0.1700
Data Index: 5855463 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8169. Min Range: -11.8169
Max Act: 11.0044. Min Act: -0.1700
Data Index: 6397447 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8169. Min Range: -11.8169
Max Act: 11.0044. Min Act: -0.1700
Data Index: 2032959 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8169. Min Range: -11.8169
Max Act: 11.0044. Min Act: -0.1700
Data Index: 7899685 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8169. Min Range: -11.8169
Max Act: 10.8169. Min Act: -0.1700
Data Index: 6620927 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8169. Min Range: -11.8169
Max Act: 10.8169. Min Act: -0.1700
Data Index: 1454035 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8169. Min Range: -11.8169
Max Act: 10.7544. Min Act: -0.1700
Data Index: 7711729 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8169. Min Range: -11.8169
Max Act: 10.8169. Min Act: -0.1700
Data Index: 6274480 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8169. Min Range: -11.8169
Max Act: 10.7544. Min Act: -0.1700
Data Index: 563333 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8169. Min Range: -11.8169
Max Act: 10.6919. Min Act: -0.1700
Data Index: 163624 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8169. Min Range: -11.8169
Max Act: 10.6919. Min Act: -0.1700
Data Index: 5008418 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8169. Min Range: -11.8169
Max Act: 10.6294. Min Act: -0.1700
Data Index: 3107856 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8169. Min Range: -11.8169
Max Act: 10.6294. Min Act: -0.1700
Data Index: 900087 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8169. Min Range: -11.8169
Max Act: 10.6294. Min Act: -0.1700
Data Index: 3699480 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8169. Min Range: -11.8169
Max Act: 10.6294. Min Act: -0.1700
Data Index: 2526382 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8169. Min Range: -11.8169
Max Act: 10.6294. Min Act: -0.1700
Data Index: 6103744 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8169. Min Range: -11.8169
Max Act: 10.6294. Min Act: -0.1700
Data Index: 6636872 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8169. Min Range: -11.8169
Max Act: 10.5669. Min Act: -0.1700
Data Index: 2744840 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19