Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2861 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9436. Min Range: -4.9436
Max Act: 4.9436. Min Act: -0.1700
Data Index: 5572004 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9436. Min Range: -4.9436
Max Act: 4.8186. Min Act: -0.1700
Data Index: 3860335 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9436. Min Range: -4.9436
Max Act: 4.8186. Min Act: -0.1700
Data Index: 4206081 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9436. Min Range: -4.9436
Max Act: 4.7874. Min Act: -0.1700
Data Index: 6342069 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9436. Min Range: -4.9436
Max Act: 4.7874. Min Act: -0.1700
Data Index: 6626357 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9436. Min Range: -4.9436
Max Act: 4.7874. Min Act: -0.1700
Data Index: 1038542 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9436. Min Range: -4.9436
Max Act: 4.7561. Min Act: -0.1700
Data Index: 3625028 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9436. Min Range: -4.9436
Max Act: 4.7561. Min Act: -0.1700
Data Index: 4697585 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9436. Min Range: -4.9436
Max Act: 4.6936. Min Act: -0.1700
Data Index: 529938 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9436. Min Range: -4.9436
Max Act: 4.7249. Min Act: -0.1700
Data Index: 2903227 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9436. Min Range: -4.9436
Max Act: 4.7561. Min Act: -0.1700
Data Index: 2895384 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9436. Min Range: -4.9436
Max Act: 4.6936. Min Act: -0.1700
Data Index: 2066895 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9436. Min Range: -4.9436
Max Act: 4.6936. Min Act: -0.1700
Data Index: 5380742 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9436. Min Range: -4.9436
Max Act: 4.6936. Min Act: -0.1700
Data Index: 6319620 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9436. Min Range: -4.9436
Max Act: 4.6936. Min Act: -0.1700
Data Index: 6683093 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9436. Min Range: -4.9436
Max Act: 4.6311. Min Act: -0.1700
Data Index: 846068 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9436. Min Range: -4.9436
Max Act: 4.5999. Min Act: -0.1700
Data Index: 5941705 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9436. Min Range: -4.9436
Max Act: 4.6311. Min Act: -0.1700
Data Index: 5830590 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9436. Min Range: -4.9436
Max Act: 4.6311. Min Act: -0.1700
Data Index: 2760830 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9436. Min Range: -4.9436
Max Act: 4.5999. Min Act: -0.1700
Data Index: 5012418 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19