Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3009 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9237. Min Range: -4.9237
Max Act: 4.9237. Min Act: -0.1700
Data Index: 6072354 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9237. Min Range: -4.9237
Max Act: 4.7362. Min Act: -0.1700
Data Index: 7567924 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9237. Min Range: -4.9237
Max Act: 4.6737. Min Act: -0.1700
Data Index: 5142898 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9237. Min Range: -4.9237
Max Act: 4.6737. Min Act: -0.1700
Data Index: 1295283 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9237. Min Range: -4.9237
Max Act: 4.6737. Min Act: -0.1700
Data Index: 7498395 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9237. Min Range: -4.9237
Max Act: 4.6425. Min Act: -0.1700
Data Index: 6283849 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9237. Min Range: -4.9237
Max Act: 4.6425. Min Act: -0.1700
Data Index: 6283853 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9237. Min Range: -4.9237
Max Act: 4.6425. Min Act: -0.1700
Data Index: 2845825 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9237. Min Range: -4.9237
Max Act: 4.6425. Min Act: -0.1700
Data Index: 6283865 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9237. Min Range: -4.9237
Max Act: 4.6425. Min Act: -0.1700
Data Index: 868770 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9237. Min Range: -4.9237
Max Act: 4.6425. Min Act: -0.1700
Data Index: 4019176 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9237. Min Range: -4.9237
Max Act: 4.6425. Min Act: -0.1700
Data Index: 6283859 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9237. Min Range: -4.9237
Max Act: 4.6425. Min Act: -0.1700
Data Index: 2258271 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9237. Min Range: -4.9237
Max Act: 4.6425. Min Act: -0.1700
Data Index: 7522513 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9237. Min Range: -4.9237
Max Act: 4.6425. Min Act: -0.1700
Data Index: 6283856 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9237. Min Range: -4.9237
Max Act: 4.6425. Min Act: -0.1700
Data Index: 7097821 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9237. Min Range: -4.9237
Max Act: 4.6425. Min Act: -0.1700
Data Index: 6283866 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9237. Min Range: -4.9237
Max Act: 4.6425. Min Act: -0.1700
Data Index: 4664619 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9237. Min Range: -4.9237
Max Act: 4.6425. Min Act: -0.1700
Data Index: 6578568 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9237. Min Range: -4.9237
Max Act: 4.6425. Min Act: -0.1700
Data Index: 1119398 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19