Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1393 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3689. Min Range: -5.3689
Max Act: 5.3689. Min Act: -0.1700
Data Index: 7473577 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3689. Min Range: -5.3689
Max Act: 5.3377. Min Act: -0.1700
Data Index: 3583751 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3689. Min Range: -5.3689
Max Act: 5.3064. Min Act: -0.1700
Data Index: 4874737 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3689. Min Range: -5.3689
Max Act: 5.3064. Min Act: -0.1700
Data Index: 8633271 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3689. Min Range: -5.3689
Max Act: 5.1814. Min Act: -0.1700
Data Index: 8590817 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3689. Min Range: -5.3689
Max Act: 5.2127. Min Act: -0.1700
Data Index: 6688715 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3689. Min Range: -5.3689
Max Act: 5.1502. Min Act: -0.1700
Data Index: 1703407 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3689. Min Range: -5.3689
Max Act: 5.1502. Min Act: -0.1700
Data Index: 3890833 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3689. Min Range: -5.3689
Max Act: 5.1814. Min Act: -0.1700
Data Index: 1752464 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3689. Min Range: -5.3689
Max Act: 5.1502. Min Act: -0.1700
Data Index: 5951280 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3689. Min Range: -5.3689
Max Act: 5.1502. Min Act: -0.1700
Data Index: 7768994 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3689. Min Range: -5.3689
Max Act: 5.1502. Min Act: -0.1700
Data Index: 4066283 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3689. Min Range: -5.3689
Max Act: 5.1502. Min Act: -0.1700
Data Index: 38288 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3689. Min Range: -5.3689
Max Act: 5.1189. Min Act: -0.1700
Data Index: 1878365 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3689. Min Range: -5.3689
Max Act: 5.1189. Min Act: -0.1700
Data Index: 1814158 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3689. Min Range: -5.3689
Max Act: 5.0877. Min Act: -0.1700
Data Index: 253796 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3689. Min Range: -5.3689
Max Act: 5.1189. Min Act: -0.1700
Data Index: 6840989 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3689. Min Range: -5.3689
Max Act: 5.1189. Min Act: -0.1700
Data Index: 6490382 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3689. Min Range: -5.3689
Max Act: 5.0877. Min Act: -0.1700
Data Index: 2646072 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3689. Min Range: -5.3689
Max Act: 5.1189. Min Act: -0.1700
Data Index: 1129692 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19