Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3431 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1025. Min Range: -5.1025
Max Act: 5.1025. Min Act: -0.1700
Data Index: 8188274 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1025. Min Range: -5.1025
Max Act: 4.8525. Min Act: -0.1700
Data Index: 2148081 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1025. Min Range: -5.1025
Max Act: 4.8525. Min Act: -0.1700
Data Index: 8746040 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1025. Min Range: -5.1025
Max Act: 4.8212. Min Act: -0.1700
Data Index: 948372 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1025. Min Range: -5.1025
Max Act: 4.8212. Min Act: -0.1700
Data Index: 8520834 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1025. Min Range: -5.1025
Max Act: 4.7900. Min Act: -0.1700
Data Index: 8694086 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1025. Min Range: -5.1025
Max Act: 4.7900. Min Act: -0.1700
Data Index: 6228089 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1025. Min Range: -5.1025
Max Act: 4.7587. Min Act: -0.1700
Data Index: 8437676 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1025. Min Range: -5.1025
Max Act: 4.7275. Min Act: -0.1700
Data Index: 5689969 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1025. Min Range: -5.1025
Max Act: 4.7587. Min Act: -0.1700
Data Index: 4086393 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1025. Min Range: -5.1025
Max Act: 4.7275. Min Act: -0.1700
Data Index: 512284 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1025. Min Range: -5.1025
Max Act: 4.7275. Min Act: -0.1700
Data Index: 5900534 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1025. Min Range: -5.1025
Max Act: 4.6962. Min Act: -0.1700
Data Index: 5807686 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1025. Min Range: -5.1025
Max Act: 4.6962. Min Act: -0.1700
Data Index: 3671457 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1025. Min Range: -5.1025
Max Act: 4.6962. Min Act: -0.1700
Data Index: 5200013 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1025. Min Range: -5.1025
Max Act: 4.6337. Min Act: -0.1700
Data Index: 8076368 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1025. Min Range: -5.1025
Max Act: 4.6650. Min Act: -0.1700
Data Index: 582069 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1025. Min Range: -5.1025
Max Act: 4.6650. Min Act: -0.1700
Data Index: 4698858 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1025. Min Range: -5.1025
Max Act: 4.6337. Min Act: -0.1700
Data Index: 4591280 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1025. Min Range: -5.1025
Max Act: 4.6337. Min Act: -0.1700
Data Index: 8366599 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19