Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2945 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.8771. Min Act: -0.1700
Data Index: 2550368 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.7833. Min Act: -0.1700
Data Index: 1527020 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.7521. Min Act: -0.1700
Data Index: 1342463 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.6896. Min Act: -0.1700
Data Index: 8475167 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.6896. Min Act: -0.1700
Data Index: 4946805 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.6271. Min Act: -0.1700
Data Index: 2849447 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.6271. Min Act: -0.1700
Data Index: 6059241 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.5646. Min Act: -0.1700
Data Index: 2974083 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.5646. Min Act: -0.1700
Data Index: 2922663 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.5646. Min Act: -0.1700
Data Index: 3954054 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.5646. Min Act: -0.1700
Data Index: 8027657 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.5021. Min Act: -0.1700
Data Index: 5181117 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.4708. Min Act: -0.1700
Data Index: 5677143 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.4708. Min Act: -0.1700
Data Index: 6509441 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.4708. Min Act: -0.1700
Data Index: 6510285 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.4708. Min Act: -0.1700
Data Index: 3602984 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.5021. Min Act: -0.1700
Data Index: 7757117 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.4396. Min Act: -0.1700
Data Index: 8339795 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.4083. Min Act: -0.1700
Data Index: 3451593 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.4083. Min Act: -0.1700
Data Index: 8222557 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19