Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3544 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3926. Min Range: -5.3926
Max Act: 5.3926. Min Act: -0.1700
Data Index: 5580421 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.7676. Min Act: -0.1700
Data Index: 947412 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.6738. Min Act: -0.1700
Data Index: 665951 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.5488. Min Act: -0.1700
Data Index: 6250142 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.4551. Min Act: -0.1700
Data Index: 5415043 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.4551. Min Act: -0.1700
Data Index: 968325 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.4238. Min Act: -0.1700
Data Index: 8455272 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.3926. Min Act: -0.1700
Data Index: 4184519 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.3926. Min Act: -0.1700
Data Index: 8735413 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.3613. Min Act: -0.1700
Data Index: 6425839 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.3926. Min Act: -0.1700
Data Index: 745350 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.3301. Min Act: -0.1700
Data Index: 7109217 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.3301. Min Act: -0.1700
Data Index: 329162 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.2988. Min Act: -0.1700
Data Index: 3312031 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.2988. Min Act: -0.1700
Data Index: 624234 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.2988. Min Act: -0.1700
Data Index: 2230299 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.2676. Min Act: -0.1700
Data Index: 2584836 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.2676. Min Act: -0.1700
Data Index: 4291062 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.2676. Min Act: -0.1700
Data Index: 3779937 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3926. Min Range: -5.3926
Max Act: 4.2363. Min Act: -0.1700
Data Index: 5265328 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19