Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1891 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1869. Min Range: -6.1869
Max Act: 6.1869. Min Act: -0.1700
Data Index: 273352 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1869. Min Range: -6.1869
Max Act: 6.1244. Min Act: -0.1700
Data Index: 7434614 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1869. Min Range: -6.1869
Max Act: 6.0619. Min Act: -0.1700
Data Index: 2675618 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.9994. Min Act: -0.1700
Data Index: 1047302 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.9056. Min Act: -0.1700
Data Index: 3700578 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.8744. Min Act: -0.1700
Data Index: 5854696 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.8119. Min Act: -0.1700
Data Index: 8176788 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.7806. Min Act: -0.1700
Data Index: 7736326 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.8119. Min Act: -0.1700
Data Index: 307663 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.7806. Min Act: -0.1700
Data Index: 5820760 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.7494. Min Act: -0.1700
Data Index: 8455837 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.7494. Min Act: -0.1700
Data Index: 1320691 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.7494. Min Act: -0.1700
Data Index: 5306129 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.7494. Min Act: -0.1700
Data Index: 8587310 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.7181. Min Act: -0.1700
Data Index: 4918757 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.7181. Min Act: -0.1700
Data Index: 4201555 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.6869. Min Act: -0.1700
Data Index: 539750 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.6244. Min Act: -0.1700
Data Index: 1630519 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.6244. Min Act: -0.1700
Data Index: 5763416 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.5931. Min Act: -0.1700
Data Index: 3012208 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19