Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2849 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3321. Min Range: -5.3321
Max Act: 5.3321. Min Act: -0.1700
Data Index: 6141433 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3321. Min Range: -5.3321
Max Act: 5.2696. Min Act: -0.1700
Data Index: 590332 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3321. Min Range: -5.3321
Max Act: 5.2071. Min Act: -0.1700
Data Index: 6237671 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3321. Min Range: -5.3321
Max Act: 5.2071. Min Act: -0.1700
Data Index: 7477245 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3321. Min Range: -5.3321
Max Act: 5.1758. Min Act: -0.1700
Data Index: 7335358 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3321. Min Range: -5.3321
Max Act: 5.1758. Min Act: -0.1699
Data Index: 803795 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3321. Min Range: -5.3321
Max Act: 5.1758. Min Act: -0.1700
Data Index: 7527736 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3321. Min Range: -5.3321
Max Act: 5.1758. Min Act: -0.1700
Data Index: 297284 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3321. Min Range: -5.3321
Max Act: 5.1446. Min Act: -0.1700
Data Index: 2703095 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3321. Min Range: -5.3321
Max Act: 5.1446. Min Act: -0.1700
Data Index: 2089890 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3321. Min Range: -5.3321
Max Act: 5.1446. Min Act: -0.1700
Data Index: 4682917 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3321. Min Range: -5.3321
Max Act: 5.1446. Min Act: -0.1700
Data Index: 8064947 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3321. Min Range: -5.3321
Max Act: 5.1133. Min Act: -0.1700
Data Index: 2579077 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3321. Min Range: -5.3321
Max Act: 5.1446. Min Act: -0.1700
Data Index: 4182986 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3321. Min Range: -5.3321
Max Act: 5.1133. Min Act: -0.1700
Data Index: 4584738 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3321. Min Range: -5.3321
Max Act: 5.1133. Min Act: -0.1700
Data Index: 451997 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3321. Min Range: -5.3321
Max Act: 5.1133. Min Act: -0.1700
Data Index: 3659451 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3321. Min Range: -5.3321
Max Act: 5.1133. Min Act: -0.1700
Data Index: 5551288 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3321. Min Range: -5.3321
Max Act: 5.1133. Min Act: -0.1700
Data Index: 1037705 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3321. Min Range: -5.3321
Max Act: 5.1133. Min Act: -0.1700
Data Index: 5582667 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19