Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 992 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.9092. Min Act: -0.1700
Data Index: 2972345 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.8779. Min Act: -0.1700
Data Index: 3737887 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.8467. Min Act: -0.1700
Data Index: 2492043 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.8467. Min Act: -0.1700
Data Index: 2572487 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.6592. Min Act: -0.1700
Data Index: 2334160 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.6279. Min Act: -0.1700
Data Index: 6203079 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.6279. Min Act: -0.1700
Data Index: 3731435 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.5967. Min Act: -0.1700
Data Index: 87558 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.6279. Min Act: -0.1700
Data Index: 4688583 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.5967. Min Act: -0.1700
Data Index: 3604892 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.5967. Min Act: -0.1700
Data Index: 5057657 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.5654. Min Act: -0.1700
Data Index: 5643118 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.5967. Min Act: -0.1700
Data Index: 5375094 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.5342. Min Act: -0.1700
Data Index: 923577 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.5654. Min Act: -0.1700
Data Index: 5082691 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.5654. Min Act: -0.1700
Data Index: 6691134 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.5342. Min Act: -0.1700
Data Index: 1374343 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.5654. Min Act: -0.1700
Data Index: 849407 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.5342. Min Act: -0.1700
Data Index: 4720379 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.5342. Min Act: -0.1700
Data Index: 100220 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19