Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4552 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2119. Min Range: -7.2119
Max Act: 7.2119. Min Act: -0.1700
Data Index: 7595981 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2119. Min Range: -7.2119
Max Act: 7.2119. Min Act: -0.1700
Data Index: 5442792 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2119. Min Range: -7.2119
Max Act: 7.1494. Min Act: -0.1700
Data Index: 672739 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2119. Min Range: -7.2119
Max Act: 7.0557. Min Act: -0.1700
Data Index: 4445205 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2119. Min Range: -7.2119
Max Act: 7.0244. Min Act: -0.1700
Data Index: 191275 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2119. Min Range: -7.2119
Max Act: 7.0244. Min Act: -0.1700
Data Index: 744673 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2119. Min Range: -7.2119
Max Act: 7.0244. Min Act: -0.1700
Data Index: 3025426 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.9932. Min Act: -0.1700
Data Index: 3547896 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.9307. Min Act: -0.1700
Data Index: 5828860 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.8994. Min Act: -0.1700
Data Index: 2479719 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.9307. Min Act: -0.1700
Data Index: 4095251 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.8994. Min Act: -0.1700
Data Index: 5082226 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.8682. Min Act: -0.1700
Data Index: 8434906 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.8369. Min Act: -0.1700
Data Index: 2420443 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.8994. Min Act: -0.1700
Data Index: 5258509 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.8994. Min Act: -0.1700
Data Index: 582114 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.8369. Min Act: -0.1700
Data Index: 8527133 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.7744. Min Act: -0.1700
Data Index: 5991405 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.7744. Min Act: -0.1700
Data Index: 4085190 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.7744. Min Act: -0.1700
Data Index: 4258928 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19