Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8092. Min Range: -6.8092
Max Act: 6.8092. Min Act: -0.1700
Data Index: 1025315 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8092. Min Range: -6.8092
Max Act: 6.7155. Min Act: -0.1700
Data Index: 7360655 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8092. Min Range: -6.8092
Max Act: 6.5905. Min Act: -0.1700
Data Index: 5744883 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8092. Min Range: -6.8092
Max Act: 6.5592. Min Act: -0.1700
Data Index: 8136126 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8092. Min Range: -6.8092
Max Act: 6.4030. Min Act: -0.1700
Data Index: 3731756 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8092. Min Range: -6.8092
Max Act: 6.4030. Min Act: -0.1700
Data Index: 8106351 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8092. Min Range: -6.8092
Max Act: 6.3405. Min Act: -0.1700
Data Index: 6822066 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8092. Min Range: -6.8092
Max Act: 6.3405. Min Act: -0.1700
Data Index: 8321744 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8092. Min Range: -6.8092
Max Act: 6.2467. Min Act: -0.1700
Data Index: 2230696 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8092. Min Range: -6.8092
Max Act: 6.2467. Min Act: -0.1700
Data Index: 3529426 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8092. Min Range: -6.8092
Max Act: 6.1842. Min Act: -0.1700
Data Index: 3129114 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8092. Min Range: -6.8092
Max Act: 6.1842. Min Act: -0.1700
Data Index: 1444090 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8092. Min Range: -6.8092
Max Act: 6.1842. Min Act: -0.1700
Data Index: 5934768 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8092. Min Range: -6.8092
Max Act: 6.1530. Min Act: -0.1700
Data Index: 6493123 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8092. Min Range: -6.8092
Max Act: 6.1530. Min Act: -0.1700
Data Index: 6813431 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8092. Min Range: -6.8092
Max Act: 6.1217. Min Act: -0.1700
Data Index: 2930577 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8092. Min Range: -6.8092
Max Act: 6.1217. Min Act: -0.1700
Data Index: 67679 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8092. Min Range: -6.8092
Max Act: 6.0905. Min Act: -0.1700
Data Index: 5123312 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8092. Min Range: -6.8092
Max Act: 6.0905. Min Act: -0.1700
Data Index: 7513638 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8092. Min Range: -6.8092
Max Act: 6.0592. Min Act: -0.1700
Data Index: 3843102 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19