Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 529 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1181. Min Range: -6.1181
Max Act: 6.1181. Min Act: -0.1700
Data Index: 240535 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1181. Min Range: -6.1181
Max Act: 6.0556. Min Act: -0.1700
Data Index: 1049503 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.8369. Min Act: -0.1700
Data Index: 4900021 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.8994. Min Act: -0.1700
Data Index: 3942341 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.8994. Min Act: -0.1700
Data Index: 582763 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.8369. Min Act: -0.1700
Data Index: 6401159 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.8369. Min Act: -0.1700
Data Index: 2178769 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7744. Min Act: -0.1700
Data Index: 3618685 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7744. Min Act: -0.1700
Data Index: 2256331 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7744. Min Act: -0.1700
Data Index: 7985524 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7119. Min Act: -0.1700
Data Index: 8276492 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7744. Min Act: -0.1700
Data Index: 5537116 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7744. Min Act: -0.1700
Data Index: 8765046 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7431. Min Act: -0.1700
Data Index: 5655911 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7744. Min Act: -0.1700
Data Index: 4080873 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7431. Min Act: -0.1700
Data Index: 657879 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7119. Min Act: -0.1700
Data Index: 8273177 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7119. Min Act: -0.1700
Data Index: 2491100 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7119. Min Act: -0.1700
Data Index: 4571009 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7431. Min Act: -0.1700
Data Index: 5854259 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19