Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3227 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0608. Min Range: -5.0608
Max Act: 5.0608. Min Act: -0.1700
Data Index: 3664136 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0608. Min Range: -5.0608
Max Act: 5.0608. Min Act: -0.1700
Data Index: 8714121 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0608. Min Range: -5.0608
Max Act: 5.0295. Min Act: -0.1700
Data Index: 803428 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0608. Min Range: -5.0608
Max Act: 4.9983. Min Act: -0.1700
Data Index: 6743622 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0608. Min Range: -5.0608
Max Act: 4.9983. Min Act: -0.1700
Data Index: 7164004 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0608. Min Range: -5.0608
Max Act: 4.9983. Min Act: -0.1700
Data Index: 5844243 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0608. Min Range: -5.0608
Max Act: 4.9670. Min Act: -0.1700
Data Index: 334124 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0608. Min Range: -5.0608
Max Act: 4.9670. Min Act: -0.1700
Data Index: 7481957 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0608. Min Range: -5.0608
Max Act: 4.9670. Min Act: -0.1700
Data Index: 3768785 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0608. Min Range: -5.0608
Max Act: 4.9358. Min Act: -0.1700
Data Index: 6581429 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0608. Min Range: -5.0608
Max Act: 4.9358. Min Act: -0.1700
Data Index: 7848063 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0608. Min Range: -5.0608
Max Act: 4.9045. Min Act: -0.1700
Data Index: 2785789 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0608. Min Range: -5.0608
Max Act: 4.8733. Min Act: -0.1700
Data Index: 143469 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0608. Min Range: -5.0608
Max Act: 4.9045. Min Act: -0.1700
Data Index: 2524266 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0608. Min Range: -5.0608
Max Act: 4.9045. Min Act: -0.1700
Data Index: 537931 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0608. Min Range: -5.0608
Max Act: 4.9045. Min Act: -0.1700
Data Index: 1077825 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0608. Min Range: -5.0608
Max Act: 4.8420. Min Act: -0.1700
Data Index: 5793872 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0608. Min Range: -5.0608
Max Act: 4.8733. Min Act: -0.1700
Data Index: 628028 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0608. Min Range: -5.0608
Max Act: 4.8733. Min Act: -0.1700
Data Index: 81478 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0608. Min Range: -5.0608
Max Act: 4.8733. Min Act: -0.1700
Data Index: 1033240 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19