Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1600 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2692. Min Range: -6.2692
Max Act: 6.2692. Min Act: -0.1700
Data Index: 1742435 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2692. Min Range: -6.2692
Max Act: 6.1129. Min Act: -0.1700
Data Index: 5701258 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2692. Min Range: -6.2692
Max Act: 6.0504. Min Act: -0.1700
Data Index: 8743150 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.9879. Min Act: -0.1700
Data Index: 1664361 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2692. Min Range: -6.2692
Max Act: 6.0192. Min Act: -0.1700
Data Index: 1988907 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.9567. Min Act: -0.1700
Data Index: 8290176 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.9567. Min Act: -0.1700
Data Index: 1316680 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.9254. Min Act: -0.1700
Data Index: 3634658 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.9254. Min Act: -0.1700
Data Index: 6517476 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.9254. Min Act: -0.1700
Data Index: 8290175 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.9254. Min Act: -0.1700
Data Index: 8678899 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.8942. Min Act: -0.1700
Data Index: 2991020 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.8942. Min Act: -0.1700
Data Index: 8619458 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.8629. Min Act: -0.1700
Data Index: 8351983 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.8942. Min Act: -0.1700
Data Index: 4203508 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.8629. Min Act: -0.1700
Data Index: 1638169 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.8629. Min Act: -0.1700
Data Index: 3096557 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.8004. Min Act: -0.1700
Data Index: 7433154 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.8317. Min Act: -0.1700
Data Index: 904670 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.8317. Min Act: -0.1700
Data Index: 1714278 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19