Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2600 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9216. Min Range: -6.9216
Max Act: 6.9216. Min Act: -0.1700
Data Index: 8127919 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9216. Min Range: -6.9216
Max Act: 6.8591. Min Act: -0.1700
Data Index: 7748702 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9216. Min Range: -6.9216
Max Act: 6.7966. Min Act: -0.1700
Data Index: 6234473 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9216. Min Range: -6.9216
Max Act: 6.7341. Min Act: -0.1700
Data Index: 1967809 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9216. Min Range: -6.9216
Max Act: 6.7341. Min Act: -0.1700
Data Index: 5262558 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9216. Min Range: -6.9216
Max Act: 6.7341. Min Act: -0.1700
Data Index: 4369489 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9216. Min Range: -6.9216
Max Act: 6.7029. Min Act: -0.1700
Data Index: 6765499 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9216. Min Range: -6.9216
Max Act: 6.6716. Min Act: -0.1700
Data Index: 4369491 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9216. Min Range: -6.9216
Max Act: 6.6716. Min Act: -0.1700
Data Index: 6765497 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9216. Min Range: -6.9216
Max Act: 6.6404. Min Act: -0.1700
Data Index: 1932051 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9216. Min Range: -6.9216
Max Act: 6.6404. Min Act: -0.1700
Data Index: 88828 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9216. Min Range: -6.9216
Max Act: 6.6404. Min Act: -0.1700
Data Index: 5588952 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9216. Min Range: -6.9216
Max Act: 6.6716. Min Act: -0.1700
Data Index: 1428019 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9216. Min Range: -6.9216
Max Act: 6.6404. Min Act: -0.1700
Data Index: 4369490 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9216. Min Range: -6.9216
Max Act: 6.6091. Min Act: -0.1700
Data Index: 781104 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9216. Min Range: -6.9216
Max Act: 6.6091. Min Act: -0.1700
Data Index: 508544 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9216. Min Range: -6.9216
Max Act: 6.6091. Min Act: -0.1700
Data Index: 5881715 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9216. Min Range: -6.9216
Max Act: 6.6091. Min Act: -0.1700
Data Index: 3946019 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9216. Min Range: -6.9216
Max Act: 6.6091. Min Act: -0.1700
Data Index: 4821129 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9216. Min Range: -6.9216
Max Act: 6.5779. Min Act: -0.1700
Data Index: 675990 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19