Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 52 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8663. Min Range: -7.8663
Max Act: 7.8663. Min Act: -0.1700
Data Index: 8620175 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8663. Min Range: -7.8663
Max Act: 7.7413. Min Act: -0.1700
Data Index: 1792067 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8663. Min Range: -7.8663
Max Act: 7.7101. Min Act: -0.1700
Data Index: 5333697 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8663. Min Range: -7.8663
Max Act: 7.6788. Min Act: -0.1700
Data Index: 6319896 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8663. Min Range: -7.8663
Max Act: 7.6163. Min Act: -0.1700
Data Index: 5777621 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8663. Min Range: -7.8663
Max Act: 7.5538. Min Act: -0.1700
Data Index: 5006208 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8663. Min Range: -7.8663
Max Act: 7.5851. Min Act: -0.1700
Data Index: 1548463 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8663. Min Range: -7.8663
Max Act: 7.5226. Min Act: -0.1700
Data Index: 8251968 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8663. Min Range: -7.8663
Max Act: 7.5538. Min Act: -0.1700
Data Index: 4928434 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8663. Min Range: -7.8663
Max Act: 7.5226. Min Act: -0.1700
Data Index: 4102086 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8663. Min Range: -7.8663
Max Act: 7.4288. Min Act: -0.1700
Data Index: 8818135 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8663. Min Range: -7.8663
Max Act: 7.4913. Min Act: -0.1700
Data Index: 3370913 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8663. Min Range: -7.8663
Max Act: 7.4288. Min Act: -0.1700
Data Index: 5798100 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8663. Min Range: -7.8663
Max Act: 7.4913. Min Act: -0.1700
Data Index: 8116046 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8663. Min Range: -7.8663
Max Act: 7.4601. Min Act: -0.1700
Data Index: 1730109 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8663. Min Range: -7.8663
Max Act: 7.4913. Min Act: -0.1700
Data Index: 6324110 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8663. Min Range: -7.8663
Max Act: 7.4288. Min Act: -0.1700
Data Index: 8341744 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8663. Min Range: -7.8663
Max Act: 7.4288. Min Act: -0.1700
Data Index: 8588903 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8663. Min Range: -7.8663
Max Act: 7.3976. Min Act: -0.1700
Data Index: 4668856 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8663. Min Range: -7.8663
Max Act: 7.4601. Min Act: -0.1700
Data Index: 7625393 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19