Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2170 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1719. Min Range: -6.1719
Max Act: 6.1719. Min Act: -0.1700
Data Index: 5126320 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1719. Min Range: -6.1719
Max Act: 6.1406. Min Act: -0.1700
Data Index: 8070756 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1719. Min Range: -6.1719
Max Act: 6.1094. Min Act: -0.1700
Data Index: 1786981 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1719. Min Range: -6.1719
Max Act: 6.0469. Min Act: -0.1700
Data Index: 8821463 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1719. Min Range: -6.1719
Max Act: 6.0156. Min Act: -0.1700
Data Index: 778752 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1719. Min Range: -6.1719
Max Act: 6.0469. Min Act: -0.1700
Data Index: 2661331 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1719. Min Range: -6.1719
Max Act: 6.0469. Min Act: -0.1700
Data Index: 1258966 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1719. Min Range: -6.1719
Max Act: 6.0156. Min Act: -0.1700
Data Index: 3644703 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1719. Min Range: -6.1719
Max Act: 6.0156. Min Act: -0.1700
Data Index: 716679 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1719. Min Range: -6.1719
Max Act: 6.0156. Min Act: -0.1700
Data Index: 1682444 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1719. Min Range: -6.1719
Max Act: 5.9844. Min Act: -0.1700
Data Index: 8669203 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1719. Min Range: -6.1719
Max Act: 5.9844. Min Act: -0.1700
Data Index: 4704866 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1719. Min Range: -6.1719
Max Act: 5.9531. Min Act: -0.1700
Data Index: 6875108 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1719. Min Range: -6.1719
Max Act: 5.9531. Min Act: -0.1700
Data Index: 7774203 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1719. Min Range: -6.1719
Max Act: 5.9219. Min Act: -0.1700
Data Index: 5466234 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1719. Min Range: -6.1719
Max Act: 5.9219. Min Act: -0.1700
Data Index: 8498639 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1719. Min Range: -6.1719
Max Act: 5.8906. Min Act: -0.1700
Data Index: 8455745 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1719. Min Range: -6.1719
Max Act: 5.9219. Min Act: -0.1700
Data Index: 3589880 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1719. Min Range: -6.1719
Max Act: 5.8906. Min Act: -0.1700
Data Index: 7975111 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1719. Min Range: -6.1719
Max Act: 5.9219. Min Act: -0.1700
Data Index: 4188899 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19