Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3283 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8880. Min Range: -4.8880
Max Act: 4.8880. Min Act: -0.1700
Data Index: 1638903 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8880. Min Range: -4.8880
Max Act: 4.8255. Min Act: -0.1700
Data Index: 6423428 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8880. Min Range: -4.8880
Max Act: 4.7630. Min Act: -0.1700
Data Index: 8430939 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8880. Min Range: -4.8880
Max Act: 4.7318. Min Act: -0.1700
Data Index: 847448 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8880. Min Range: -4.8880
Max Act: 4.7005. Min Act: -0.1700
Data Index: 7342320 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8880. Min Range: -4.8880
Max Act: 4.6068. Min Act: -0.1700
Data Index: 5568827 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8880. Min Range: -4.8880
Max Act: 4.6068. Min Act: -0.1700
Data Index: 4904334 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8880. Min Range: -4.8880
Max Act: 4.5755. Min Act: -0.1700
Data Index: 4991880 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8880. Min Range: -4.8880
Max Act: 4.5443. Min Act: -0.1700
Data Index: 5906582 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8880. Min Range: -4.8880
Max Act: 4.5443. Min Act: -0.1700
Data Index: 862057 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8880. Min Range: -4.8880
Max Act: 4.5755. Min Act: -0.1700
Data Index: 2196072 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8880. Min Range: -4.8880
Max Act: 4.5130. Min Act: -0.1700
Data Index: 2846633 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8880. Min Range: -4.8880
Max Act: 4.4818. Min Act: -0.1700
Data Index: 5871030 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8880. Min Range: -4.8880
Max Act: 4.4505. Min Act: -0.1700
Data Index: 6089247 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8880. Min Range: -4.8880
Max Act: 4.4505. Min Act: -0.1700
Data Index: 654689 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8880. Min Range: -4.8880
Max Act: 4.4505. Min Act: -0.1700
Data Index: 6166590 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8880. Min Range: -4.8880
Max Act: 4.4193. Min Act: -0.1700
Data Index: 5894616 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8880. Min Range: -4.8880
Max Act: 4.4193. Min Act: -0.1700
Data Index: 7091957 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8880. Min Range: -4.8880
Max Act: 4.3880. Min Act: -0.1700
Data Index: 3683582 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8880. Min Range: -4.8880
Max Act: 4.4193. Min Act: -0.1700
Data Index: 556692 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19