Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3280 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0025. Min Range: -5.0025
Max Act: 5.0025. Min Act: -0.1700
Data Index: 5518041 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0025. Min Range: -5.0025
Max Act: 4.9712. Min Act: -0.1700
Data Index: 4146066 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0025. Min Range: -5.0025
Max Act: 4.8462. Min Act: -0.1700
Data Index: 484656 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0025. Min Range: -5.0025
Max Act: 4.8150. Min Act: -0.1700
Data Index: 734280 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0025. Min Range: -5.0025
Max Act: 4.8150. Min Act: -0.1700
Data Index: 5729615 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0025. Min Range: -5.0025
Max Act: 4.7525. Min Act: -0.1700
Data Index: 6590493 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0025. Min Range: -5.0025
Max Act: 4.7525. Min Act: -0.1700
Data Index: 4786642 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0025. Min Range: -5.0025
Max Act: 4.7525. Min Act: -0.1700
Data Index: 566681 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0025. Min Range: -5.0025
Max Act: 4.7212. Min Act: -0.1700
Data Index: 5530931 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0025. Min Range: -5.0025
Max Act: 4.7212. Min Act: -0.1700
Data Index: 2252045 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0025. Min Range: -5.0025
Max Act: 4.7212. Min Act: -0.1700
Data Index: 2304364 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0025. Min Range: -5.0025
Max Act: 4.7212. Min Act: -0.1700
Data Index: 7031266 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0025. Min Range: -5.0025
Max Act: 4.6900. Min Act: -0.1700
Data Index: 6932392 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0025. Min Range: -5.0025
Max Act: 4.6900. Min Act: -0.1700
Data Index: 7034229 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0025. Min Range: -5.0025
Max Act: 4.6587. Min Act: -0.1700
Data Index: 7592047 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0025. Min Range: -5.0025
Max Act: 4.6900. Min Act: -0.1700
Data Index: 5574311 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0025. Min Range: -5.0025
Max Act: 4.6275. Min Act: -0.1700
Data Index: 6703093 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0025. Min Range: -5.0025
Max Act: 4.6587. Min Act: -0.1700
Data Index: 8201745 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0025. Min Range: -5.0025
Max Act: 4.6587. Min Act: -0.1700
Data Index: 6047275 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0025. Min Range: -5.0025
Max Act: 4.6275. Min Act: -0.1700
Data Index: 3637923 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19