Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2558 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0915. Min Range: -4.0915
Max Act: 4.0915. Min Act: -0.1700
Data Index: 7707777 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0915. Min Range: -4.0915
Max Act: 3.9977. Min Act: -0.1700
Data Index: 8768726 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0915. Min Range: -4.0915
Max Act: 3.9665. Min Act: -0.1700
Data Index: 6511200 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0915. Min Range: -4.0915
Max Act: 3.9665. Min Act: -0.1700
Data Index: 4843582 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0915. Min Range: -4.0915
Max Act: 3.9352. Min Act: -0.1700
Data Index: 7516778 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0915. Min Range: -4.0915
Max Act: 3.9039. Min Act: -0.1700
Data Index: 1182594 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0915. Min Range: -4.0915
Max Act: 3.9039. Min Act: -0.1700
Data Index: 1532439 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0915. Min Range: -4.0915
Max Act: 3.9039. Min Act: -0.1700
Data Index: 6092626 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0915. Min Range: -4.0915
Max Act: 3.9039. Min Act: -0.1700
Data Index: 2098294 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0915. Min Range: -4.0915
Max Act: 3.9039. Min Act: -0.1700
Data Index: 1850048 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0915. Min Range: -4.0915
Max Act: 3.8727. Min Act: -0.1700
Data Index: 8476507 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0915. Min Range: -4.0915
Max Act: 3.8727. Min Act: -0.1700
Data Index: 8607600 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0915. Min Range: -4.0915
Max Act: 3.8727. Min Act: -0.1700
Data Index: 5415699 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0915. Min Range: -4.0915
Max Act: 3.8727. Min Act: -0.1700
Data Index: 6005516 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0915. Min Range: -4.0915
Max Act: 3.8727. Min Act: -0.1700
Data Index: 8476506 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0915. Min Range: -4.0915
Max Act: 3.8727. Min Act: -0.1700
Data Index: 4560543 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0915. Min Range: -4.0915
Max Act: 3.8727. Min Act: -0.1700
Data Index: 3447705 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0915. Min Range: -4.0915
Max Act: 3.8414. Min Act: -0.1700
Data Index: 1351278 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0915. Min Range: -4.0915
Max Act: 3.8414. Min Act: -0.1700
Data Index: 6005515 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0915. Min Range: -4.0915
Max Act: 3.8414. Min Act: -0.1700
Data Index: 6912460 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19