Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6090 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1919. Min Range: -7.1919
Max Act: 7.1919. Min Act: -0.1700
Data Index: 4268090 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1919. Min Range: -7.1919
Max Act: 7.0982. Min Act: -0.1700
Data Index: 7369268 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1919. Min Range: -7.1919
Max Act: 7.0044. Min Act: -0.1700
Data Index: 8310050 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1919. Min Range: -7.1919
Max Act: 6.9732. Min Act: -0.1700
Data Index: 4918000 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1919. Min Range: -7.1919
Max Act: 6.9732. Min Act: -0.1700
Data Index: 2544338 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1919. Min Range: -7.1919
Max Act: 6.8794. Min Act: -0.1700
Data Index: 132592 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1919. Min Range: -7.1919
Max Act: 6.8794. Min Act: -0.1700
Data Index: 4388810 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1919. Min Range: -7.1919
Max Act: 6.8482. Min Act: -0.1700
Data Index: 6956399 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1919. Min Range: -7.1919
Max Act: 6.8482. Min Act: -0.1700
Data Index: 7883583 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1919. Min Range: -7.1919
Max Act: 6.8482. Min Act: -0.1700
Data Index: 7202938 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1919. Min Range: -7.1919
Max Act: 6.8482. Min Act: -0.1700
Data Index: 3257264 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1919. Min Range: -7.1919
Max Act: 6.7857. Min Act: -0.1700
Data Index: 6503847 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1919. Min Range: -7.1919
Max Act: 6.7857. Min Act: -0.1700
Data Index: 6442952 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1919. Min Range: -7.1919
Max Act: 6.7857. Min Act: -0.1700
Data Index: 4565007 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1919. Min Range: -7.1919
Max Act: 6.7857. Min Act: -0.1700
Data Index: 6042875 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1919. Min Range: -7.1919
Max Act: 6.7857. Min Act: -0.1700
Data Index: 929644 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1919. Min Range: -7.1919
Max Act: 6.7857. Min Act: -0.1700
Data Index: 4501234 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1919. Min Range: -7.1919
Max Act: 6.7232. Min Act: -0.1700
Data Index: 592500 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1919. Min Range: -7.1919
Max Act: 6.7544. Min Act: -0.1700
Data Index: 5861267 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1919. Min Range: -7.1919
Max Act: 6.7232. Min Act: -0.1700
Data Index: 5562601 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19