Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1876 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0014. Min Range: -4.0014
Max Act: 4.0014. Min Act: -0.1700
Data Index: 8458096 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0014. Min Range: -4.0014
Max Act: 3.8451. Min Act: -0.1700
Data Index: 5635535 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0014. Min Range: -4.0014
Max Act: 3.7825. Min Act: -0.1700
Data Index: 7521290 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0014. Min Range: -4.0014
Max Act: 3.7825. Min Act: -0.1700
Data Index: 6444649 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0014. Min Range: -4.0014
Max Act: 3.7513. Min Act: -0.1700
Data Index: 6547748 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0014. Min Range: -4.0014
Max Act: 3.7513. Min Act: -0.1700
Data Index: 3766121 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0014. Min Range: -4.0014
Max Act: 3.7356. Min Act: -0.1700
Data Index: 5929739 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0014. Min Range: -4.0014
Max Act: 3.7200. Min Act: -0.1700
Data Index: 1470379 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0014. Min Range: -4.0014
Max Act: 3.7200. Min Act: -0.1700
Data Index: 6432287 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0014. Min Range: -4.0014
Max Act: 3.7043. Min Act: -0.1700
Data Index: 2293450 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0014. Min Range: -4.0014
Max Act: 3.7043. Min Act: -0.1700
Data Index: 3689767 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0014. Min Range: -4.0014
Max Act: 3.7043. Min Act: -0.1700
Data Index: 8715823 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0014. Min Range: -4.0014
Max Act: 3.6574. Min Act: -0.1700
Data Index: 4333890 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0014. Min Range: -4.0014
Max Act: 3.6574. Min Act: -0.1700
Data Index: 334065 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0014. Min Range: -4.0014
Max Act: 3.6574. Min Act: -0.1700
Data Index: 6444654 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0014. Min Range: -4.0014
Max Act: 3.6418. Min Act: -0.1700
Data Index: 8699476 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0014. Min Range: -4.0014
Max Act: 3.6418. Min Act: -0.1700
Data Index: 3260937 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0014. Min Range: -4.0014
Max Act: 3.6261. Min Act: -0.1700
Data Index: 27195 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0014. Min Range: -4.0014
Max Act: 3.6105. Min Act: -0.1700
Data Index: 7939820 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0014. Min Range: -4.0014
Max Act: 3.6261. Min Act: -0.1700
Data Index: 5367918 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19