Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1912 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2363. Min Range: -7.2363
Max Act: 7.2363. Min Act: -0.1700
Data Index: 969492 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2363. Min Range: -7.2363
Max Act: 6.7363. Min Act: -0.1700
Data Index: 7609048 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2363. Min Range: -7.2363
Max Act: 6.7050. Min Act: -0.1700
Data Index: 1773995 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2363. Min Range: -7.2363
Max Act: 6.7050. Min Act: -0.1700
Data Index: 7537477 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2363. Min Range: -7.2363
Max Act: 6.6425. Min Act: -0.1700
Data Index: 3469147 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2363. Min Range: -7.2363
Max Act: 6.5800. Min Act: -0.1700
Data Index: 3434116 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2363. Min Range: -7.2363
Max Act: 6.5800. Min Act: -0.1700
Data Index: 5626968 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2363. Min Range: -7.2363
Max Act: 6.5800. Min Act: -0.1700
Data Index: 5099362 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2363. Min Range: -7.2363
Max Act: 6.4863. Min Act: -0.1700
Data Index: 2448625 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2363. Min Range: -7.2363
Max Act: 6.4863. Min Act: -0.1700
Data Index: 3521858 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2363. Min Range: -7.2363
Max Act: 6.4550. Min Act: -0.1700
Data Index: 4853657 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2363. Min Range: -7.2363
Max Act: 6.4550. Min Act: -0.1700
Data Index: 5463986 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2363. Min Range: -7.2363
Max Act: 6.4550. Min Act: -0.1700
Data Index: 6388305 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2363. Min Range: -7.2363
Max Act: 6.3925. Min Act: -0.1700
Data Index: 5589088 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2363. Min Range: -7.2363
Max Act: 6.3613. Min Act: -0.1700
Data Index: 2392150 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2363. Min Range: -7.2363
Max Act: 6.3613. Min Act: -0.1700
Data Index: 8196515 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2363. Min Range: -7.2363
Max Act: 6.3300. Min Act: -0.1700
Data Index: 6970597 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2363. Min Range: -7.2363
Max Act: 6.3300. Min Act: -0.1700
Data Index: 5055579 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2363. Min Range: -7.2363
Max Act: 6.2988. Min Act: -0.1700
Data Index: 8196618 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2363. Min Range: -7.2363
Max Act: 6.2988. Min Act: -0.1700
Data Index: 8238267 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19