Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 648 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6657. Min Range: -3.6657
Max Act: 3.6657. Min Act: -0.1700
Data Index: 1739166 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6657. Min Range: -3.6657
Max Act: 3.6344. Min Act: -0.1700
Data Index: 3578038 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6657. Min Range: -3.6657
Max Act: 3.6657. Min Act: -0.1700
Data Index: 1494716 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6657. Min Range: -3.6657
Max Act: 3.6657. Min Act: -0.1700
Data Index: 1013163 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6657. Min Range: -3.6657
Max Act: 3.6344. Min Act: -0.1700
Data Index: 699444 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6657. Min Range: -3.6657
Max Act: 3.6031. Min Act: -0.1700
Data Index: 217723 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6657. Min Range: -3.6657
Max Act: 3.6344. Min Act: -0.1700
Data Index: 6616451 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6657. Min Range: -3.6657
Max Act: 3.6344. Min Act: -0.1700
Data Index: 3257519 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6657. Min Range: -3.6657
Max Act: 3.6344. Min Act: -0.1700
Data Index: 434033 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6657. Min Range: -3.6657
Max Act: 3.6657. Min Act: -0.1700
Data Index: 5765054 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6657. Min Range: -3.6657
Max Act: 3.6344. Min Act: -0.1700
Data Index: 5741284 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6657. Min Range: -3.6657
Max Act: 3.6344. Min Act: -0.1699
Data Index: 5561965 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6657. Min Range: -3.6657
Max Act: 3.6344. Min Act: -0.1700
Data Index: 8285885 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6657. Min Range: -3.6657
Max Act: 3.6031. Min Act: -0.1700
Data Index: 4528575 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6657. Min Range: -3.6657
Max Act: 3.6344. Min Act: -0.1700
Data Index: 4426745 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6657. Min Range: -3.6657
Max Act: 3.6031. Min Act: -0.1700
Data Index: 663247 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6657. Min Range: -3.6657
Max Act: 3.5718. Min Act: -0.1700
Data Index: 7831767 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6657. Min Range: -3.6657
Max Act: 3.6031. Min Act: -0.1700
Data Index: 3858663 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6657. Min Range: -3.6657
Max Act: 3.6031. Min Act: -0.1700
Data Index: 8265223 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6657. Min Range: -3.6657
Max Act: 3.6344. Min Act: -0.1700
Data Index: 8265665 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19