Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1266 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.5723. Min Act: -0.1700
Data Index: 7799888 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.4161. Min Act: -0.1700
Data Index: 1288935 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.2598. Min Act: -0.1700
Data Index: 4937917 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.2286. Min Act: -0.1700
Data Index: 763807 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.1973. Min Act: -0.1700
Data Index: 6445063 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.1661. Min Act: -0.1700
Data Index: 7340155 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.1973. Min Act: -0.1700
Data Index: 3642141 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.1661. Min Act: -0.1700
Data Index: 1656796 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.1661. Min Act: -0.1700
Data Index: 3093125 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.1036. Min Act: -0.1700
Data Index: 4862843 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.1036. Min Act: -0.1700
Data Index: 8483460 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.1036. Min Act: -0.1700
Data Index: 4341562 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.1036. Min Act: -0.1700
Data Index: 6539678 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.0723. Min Act: -0.1700
Data Index: 2896854 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.0411. Min Act: -0.1700
Data Index: 31245 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.0411. Min Act: -0.1700
Data Index: 4449324 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.0411. Min Act: -0.1700
Data Index: 7812698 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.0411. Min Act: -0.1700
Data Index: 3521513 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.0411. Min Act: -0.1700
Data Index: 8017970 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.0098. Min Act: -0.1700
Data Index: 7051862 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19