Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1195 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8886. Min Range: -7.8886
Max Act: 7.8886. Min Act: -0.1700
Data Index: 3092774 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8886. Min Range: -7.8886
Max Act: 7.0449. Min Act: -0.1700
Data Index: 6786291 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8886. Min Range: -7.8886
Max Act: 7.0449. Min Act: -0.1700
Data Index: 7280743 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8886. Min Range: -7.8886
Max Act: 6.9511. Min Act: -0.1700
Data Index: 1003234 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8886. Min Range: -7.8886
Max Act: 6.8886. Min Act: -0.1700
Data Index: 2809458 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8886. Min Range: -7.8886
Max Act: 6.8261. Min Act: -0.1700
Data Index: 4144094 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8886. Min Range: -7.8886
Max Act: 6.7636. Min Act: -0.1700
Data Index: 322191 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8886. Min Range: -7.8886
Max Act: 6.7324. Min Act: -0.1700
Data Index: 2315510 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8886. Min Range: -7.8886
Max Act: 6.6699. Min Act: -0.1700
Data Index: 1019837 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8886. Min Range: -7.8886
Max Act: 6.6699. Min Act: -0.1700
Data Index: 1621017 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8886. Min Range: -7.8886
Max Act: 6.6386. Min Act: -0.1700
Data Index: 7433769 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8886. Min Range: -7.8886
Max Act: 6.6386. Min Act: -0.1700
Data Index: 656551 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8886. Min Range: -7.8886
Max Act: 6.6386. Min Act: -0.1700
Data Index: 21327 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8886. Min Range: -7.8886
Max Act: 6.6699. Min Act: -0.1700
Data Index: 3889848 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8886. Min Range: -7.8886
Max Act: 6.6074. Min Act: -0.1700
Data Index: 4527688 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8886. Min Range: -7.8886
Max Act: 6.6074. Min Act: -0.1700
Data Index: 5754373 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8886. Min Range: -7.8886
Max Act: 6.5761. Min Act: -0.1700
Data Index: 8828177 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8886. Min Range: -7.8886
Max Act: 6.5449. Min Act: -0.1700
Data Index: 2979794 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8886. Min Range: -7.8886
Max Act: 6.5449. Min Act: -0.1700
Data Index: 1874827 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8886. Min Range: -7.8886
Max Act: 6.5136. Min Act: -0.1700
Data Index: 854808 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19