Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3596 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9749. Min Range: -6.9749
Max Act: 6.9749. Min Act: -0.1700
Data Index: 7802454 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9749. Min Range: -6.9749
Max Act: 6.6937. Min Act: -0.1700
Data Index: 348058 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9749. Min Range: -6.9749
Max Act: 6.5999. Min Act: -0.1700
Data Index: 2606895 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9749. Min Range: -6.9749
Max Act: 6.5687. Min Act: -0.1700
Data Index: 7993367 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9749. Min Range: -6.9749
Max Act: 6.4749. Min Act: -0.1700
Data Index: 3905265 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9749. Min Range: -6.9749
Max Act: 6.4437. Min Act: -0.1700
Data Index: 656638 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9749. Min Range: -6.9749
Max Act: 6.4749. Min Act: -0.1700
Data Index: 2511506 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9749. Min Range: -6.9749
Max Act: 6.4437. Min Act: -0.1700
Data Index: 6703691 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9749. Min Range: -6.9749
Max Act: 6.4437. Min Act: -0.1700
Data Index: 3803042 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9749. Min Range: -6.9749
Max Act: 6.4124. Min Act: -0.1700
Data Index: 2775594 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9749. Min Range: -6.9749
Max Act: 6.4124. Min Act: -0.1700
Data Index: 6605149 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9749. Min Range: -6.9749
Max Act: 6.3499. Min Act: -0.1700
Data Index: 6056662 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9749. Min Range: -6.9749
Max Act: 6.3812. Min Act: -0.1700
Data Index: 7513719 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9749. Min Range: -6.9749
Max Act: 6.3812. Min Act: -0.1700
Data Index: 587513 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9749. Min Range: -6.9749
Max Act: 6.3499. Min Act: -0.1700
Data Index: 4511655 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9749. Min Range: -6.9749
Max Act: 6.3499. Min Act: -0.1700
Data Index: 1673152 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9749. Min Range: -6.9749
Max Act: 6.3499. Min Act: -0.1700
Data Index: 5158195 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9749. Min Range: -6.9749
Max Act: 6.3499. Min Act: -0.1700
Data Index: 321208 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9749. Min Range: -6.9749
Max Act: 6.3499. Min Act: -0.1700
Data Index: 6442827 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9749. Min Range: -6.9749
Max Act: 6.3499. Min Act: -0.1700
Data Index: 110757 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19