Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5690 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9612. Min Range: -3.9612
Max Act: 3.9612. Min Act: -0.1700
Data Index: 538457 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9612. Min Range: -3.9612
Max Act: 3.8674. Min Act: -0.1700
Data Index: 8043723 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9612. Min Range: -3.9612
Max Act: 3.8674. Min Act: -0.1700
Data Index: 8463060 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9612. Min Range: -3.9612
Max Act: 3.8674. Min Act: -0.1700
Data Index: 2198710 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9612. Min Range: -3.9612
Max Act: 3.8674. Min Act: -0.1700
Data Index: 4329760 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9612. Min Range: -3.9612
Max Act: 3.8674. Min Act: -0.1700
Data Index: 4327197 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9612. Min Range: -3.9612
Max Act: 3.8362. Min Act: -0.1700
Data Index: 3740101 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9612. Min Range: -3.9612
Max Act: 3.8362. Min Act: -0.1700
Data Index: 5664502 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9612. Min Range: -3.9612
Max Act: 3.8362. Min Act: -0.1700
Data Index: 7598662 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9612. Min Range: -3.9612
Max Act: 3.8049. Min Act: -0.1700
Data Index: 8020421 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9612. Min Range: -3.9612
Max Act: 3.8049. Min Act: -0.1700
Data Index: 7058522 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9612. Min Range: -3.9612
Max Act: 3.8049. Min Act: -0.1700
Data Index: 2323193 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9612. Min Range: -3.9612
Max Act: 3.7736. Min Act: -0.1700
Data Index: 2668709 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9612. Min Range: -3.9612
Max Act: 3.7736. Min Act: -0.1700
Data Index: 64679 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9612. Min Range: -3.9612
Max Act: 3.7736. Min Act: -0.1700
Data Index: 3586096 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9612. Min Range: -3.9612
Max Act: 3.7736. Min Act: -0.1700
Data Index: 296616 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9612. Min Range: -3.9612
Max Act: 3.7736. Min Act: -0.1700
Data Index: 7129932 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9612. Min Range: -3.9612
Max Act: 3.7736. Min Act: -0.1700
Data Index: 3208749 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9612. Min Range: -3.9612
Max Act: 3.7736. Min Act: -0.1700
Data Index: 977893 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9612. Min Range: -3.9612
Max Act: 3.7736. Min Act: -0.1700
Data Index: 4751111 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19