Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3264 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0477. Min Range: -4.0477
Max Act: 4.0477. Min Act: -0.1700
Data Index: 227461 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0477. Min Range: -4.0477
Max Act: 3.8601. Min Act: -0.1700
Data Index: 5748483 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0477. Min Range: -4.0477
Max Act: 3.8289. Min Act: -0.1700
Data Index: 3586842 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0477. Min Range: -4.0477
Max Act: 3.8132. Min Act: -0.1700
Data Index: 986523 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0477. Min Range: -4.0477
Max Act: 3.7820. Min Act: -0.1700
Data Index: 5032033 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0477. Min Range: -4.0477
Max Act: 3.7976. Min Act: -0.1700
Data Index: 8791202 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0477. Min Range: -4.0477
Max Act: 3.7976. Min Act: -0.1700
Data Index: 6320287 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0477. Min Range: -4.0477
Max Act: 3.7976. Min Act: -0.1700
Data Index: 855081 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0477. Min Range: -4.0477
Max Act: 3.7820. Min Act: -0.1700
Data Index: 5905008 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0477. Min Range: -4.0477
Max Act: 3.7350. Min Act: -0.1700
Data Index: 3318688 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0477. Min Range: -4.0477
Max Act: 3.7507. Min Act: -0.1700
Data Index: 636866 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0477. Min Range: -4.0477
Max Act: 3.7194. Min Act: -0.1700
Data Index: 7207416 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0477. Min Range: -4.0477
Max Act: 3.7194. Min Act: -0.1700
Data Index: 7171696 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0477. Min Range: -4.0477
Max Act: 3.7194. Min Act: -0.1700
Data Index: 6946017 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0477. Min Range: -4.0477
Max Act: 3.7350. Min Act: -0.1700
Data Index: 2525129 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0477. Min Range: -4.0477
Max Act: 3.7507. Min Act: -0.1700
Data Index: 8430872 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0477. Min Range: -4.0477
Max Act: 3.7194. Min Act: -0.1700
Data Index: 7471299 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0477. Min Range: -4.0477
Max Act: 3.6725. Min Act: -0.1700
Data Index: 6058591 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0477. Min Range: -4.0477
Max Act: 3.6881. Min Act: -0.1700
Data Index: 3606171 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0477. Min Range: -4.0477
Max Act: 3.6881. Min Act: -0.1700
Data Index: 7944509 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19