Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8463. Min Range: -10.8463
Max Act: 10.8463. Min Act: -0.1700
Data Index: 4135857 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8463. Min Range: -10.8463
Max Act: 10.8463. Min Act: -0.1700
Data Index: 3237924 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8463. Min Range: -10.8463
Max Act: 10.5963. Min Act: -0.1700
Data Index: 5918287 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8463. Min Range: -10.8463
Max Act: 10.5338. Min Act: -0.1700
Data Index: 6070683 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8463. Min Range: -10.8463
Max Act: 10.5338. Min Act: -0.1700
Data Index: 6628249 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8463. Min Range: -10.8463
Max Act: 10.4088. Min Act: -0.1700
Data Index: 5025147 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8463. Min Range: -10.8463
Max Act: 10.4088. Min Act: -0.1700
Data Index: 4745752 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8463. Min Range: -10.8463
Max Act: 10.4713. Min Act: -0.1700
Data Index: 1499163 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8463. Min Range: -10.8463
Max Act: 10.3463. Min Act: -0.1700
Data Index: 6163112 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8463. Min Range: -10.8463
Max Act: 10.2838. Min Act: -0.1700
Data Index: 4184215 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8463. Min Range: -10.8463
Max Act: 10.2838. Min Act: -0.1700
Data Index: 1739426 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8463. Min Range: -10.8463
Max Act: 10.2213. Min Act: -0.1700
Data Index: 2969503 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8463. Min Range: -10.8463
Max Act: 10.2213. Min Act: -0.1700
Data Index: 6763574 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8463. Min Range: -10.8463
Max Act: 10.2213. Min Act: -0.1700
Data Index: 7165869 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8463. Min Range: -10.8463
Max Act: 10.2213. Min Act: -0.1700
Data Index: 7974994 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8463. Min Range: -10.8463
Max Act: 10.0963. Min Act: -0.1700
Data Index: 2011980 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8463. Min Range: -10.8463
Max Act: 10.0338. Min Act: -0.1700
Data Index: 6791923 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8463. Min Range: -10.8463
Max Act: 10.0338. Min Act: -0.1700
Data Index: 6553714 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8463. Min Range: -10.8463
Max Act: 10.0338. Min Act: -0.1700
Data Index: 7479451 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8463. Min Range: -10.8463
Max Act: 10.0338. Min Act: -0.1700
Data Index: 3320117 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19