Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2977 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0711. Min Range: -6.0711
Max Act: 6.0711. Min Act: -0.1700
Data Index: 8584831 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0711. Min Range: -6.0711
Max Act: 5.9774. Min Act: -0.1700
Data Index: 2256922 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0711. Min Range: -6.0711
Max Act: 5.8836. Min Act: -0.1700
Data Index: 8169922 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0711. Min Range: -6.0711
Max Act: 5.8524. Min Act: -0.1700
Data Index: 174095 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0711. Min Range: -6.0711
Max Act: 5.8211. Min Act: -0.1700
Data Index: 5546464 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0711. Min Range: -6.0711
Max Act: 5.8211. Min Act: -0.1700
Data Index: 812528 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0711. Min Range: -6.0711
Max Act: 5.7899. Min Act: -0.1700
Data Index: 71562 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0711. Min Range: -6.0711
Max Act: 5.7899. Min Act: -0.1700
Data Index: 174104 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0711. Min Range: -6.0711
Max Act: 5.7586. Min Act: -0.1700
Data Index: 5083305 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0711. Min Range: -6.0711
Max Act: 5.7586. Min Act: -0.1700
Data Index: 7082784 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0711. Min Range: -6.0711
Max Act: 5.7586. Min Act: -0.1700
Data Index: 4883048 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0711. Min Range: -6.0711
Max Act: 5.7274. Min Act: -0.1700
Data Index: 5083297 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0711. Min Range: -6.0711
Max Act: 5.7274. Min Act: -0.1700
Data Index: 5127964 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0711. Min Range: -6.0711
Max Act: 5.7274. Min Act: -0.1700
Data Index: 5966944 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0711. Min Range: -6.0711
Max Act: 5.6961. Min Act: -0.1700
Data Index: 6483755 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0711. Min Range: -6.0711
Max Act: 5.6961. Min Act: -0.1700
Data Index: 1250090 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0711. Min Range: -6.0711
Max Act: 5.6649. Min Act: -0.1700
Data Index: 7192505 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0711. Min Range: -6.0711
Max Act: 5.6649. Min Act: -0.1700
Data Index: 1875605 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0711. Min Range: -6.0711
Max Act: 5.6336. Min Act: -0.1700
Data Index: 7764336 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0711. Min Range: -6.0711
Max Act: 5.6336. Min Act: -0.1700
Data Index: 1375910 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19