Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4064 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8629. Min Range: -7.8629
Max Act: 7.8629. Min Act: -0.1700
Data Index: 1571096 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8629. Min Range: -7.8629
Max Act: 7.3317. Min Act: -0.1700
Data Index: 3298400 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8629. Min Range: -7.8629
Max Act: 7.2692. Min Act: -0.1700
Data Index: 1895089 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8629. Min Range: -7.8629
Max Act: 7.2379. Min Act: -0.1700
Data Index: 3321965 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8629. Min Range: -7.8629
Max Act: 7.0192. Min Act: -0.1700
Data Index: 336269 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8629. Min Range: -7.8629
Max Act: 6.8629. Min Act: -0.1700
Data Index: 3889006 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8629. Min Range: -7.8629
Max Act: 6.8317. Min Act: -0.1700
Data Index: 1342290 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8629. Min Range: -7.8629
Max Act: 6.7379. Min Act: -0.1700
Data Index: 907253 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8629. Min Range: -7.8629
Max Act: 6.7067. Min Act: -0.1700
Data Index: 5441451 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8629. Min Range: -7.8629
Max Act: 6.6754. Min Act: -0.1700
Data Index: 1420977 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8629. Min Range: -7.8629
Max Act: 6.6442. Min Act: -0.1700
Data Index: 7848093 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8629. Min Range: -7.8629
Max Act: 6.6442. Min Act: -0.1700
Data Index: 1879448 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8629. Min Range: -7.8629
Max Act: 6.6129. Min Act: -0.1700
Data Index: 5610015 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8629. Min Range: -7.8629
Max Act: 6.4879. Min Act: -0.1700
Data Index: 8464178 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8629. Min Range: -7.8629
Max Act: 6.4567. Min Act: -0.1700
Data Index: 7174415 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8629. Min Range: -7.8629
Max Act: 6.4567. Min Act: -0.1700
Data Index: 3495140 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8629. Min Range: -7.8629
Max Act: 6.4254. Min Act: -0.1700
Data Index: 8709990 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8629. Min Range: -7.8629
Max Act: 6.3942. Min Act: -0.1700
Data Index: 6057074 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8629. Min Range: -7.8629
Max Act: 6.3942. Min Act: -0.1700
Data Index: 1479758 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8629. Min Range: -7.8629
Max Act: 6.3629. Min Act: -0.1700
Data Index: 1517180 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19