Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3638 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8700. Min Range: -5.8700
Max Act: 5.8700. Min Act: -0.1700
Data Index: 3962666 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8700. Min Range: -5.8700
Max Act: 5.8700. Min Act: -0.1700
Data Index: 2018454 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8700. Min Range: -5.8700
Max Act: 5.8075. Min Act: -0.1700
Data Index: 3897956 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8700. Min Range: -5.8700
Max Act: 5.8075. Min Act: -0.1700
Data Index: 4432818 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8700. Min Range: -5.8700
Max Act: 5.7138. Min Act: -0.1700
Data Index: 8578196 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8700. Min Range: -5.8700
Max Act: 5.7138. Min Act: -0.1700
Data Index: 1734185 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8700. Min Range: -5.8700
Max Act: 5.7138. Min Act: -0.1700
Data Index: 8271398 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8700. Min Range: -5.8700
Max Act: 5.6825. Min Act: -0.1700
Data Index: 5172420 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8700. Min Range: -5.8700
Max Act: 5.6825. Min Act: -0.1700
Data Index: 6091750 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8700. Min Range: -5.8700
Max Act: 5.6825. Min Act: -0.1700
Data Index: 755525 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8700. Min Range: -5.8700
Max Act: 5.6825. Min Act: -0.1700
Data Index: 1499481 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8700. Min Range: -5.8700
Max Act: 5.6513. Min Act: -0.1700
Data Index: 275265 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8700. Min Range: -5.8700
Max Act: 5.6513. Min Act: -0.1700
Data Index: 6864383 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8700. Min Range: -5.8700
Max Act: 5.6200. Min Act: -0.1700
Data Index: 2487049 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8700. Min Range: -5.8700
Max Act: 5.5888. Min Act: -0.1700
Data Index: 6397384 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8700. Min Range: -5.8700
Max Act: 5.5888. Min Act: -0.1700
Data Index: 2863668 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8700. Min Range: -5.8700
Max Act: 5.5888. Min Act: -0.1700
Data Index: 4078939 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8700. Min Range: -5.8700
Max Act: 5.5888. Min Act: -0.1700
Data Index: 5920687 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8700. Min Range: -5.8700
Max Act: 5.5888. Min Act: -0.1700
Data Index: 1549741 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8700. Min Range: -5.8700
Max Act: 5.5888. Min Act: -0.1700
Data Index: 5456962 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19