Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2771 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.9413. Min Act: -0.1700
Data Index: 3475817 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.8788. Min Act: -0.1700
Data Index: 1057130 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.8163. Min Act: -0.1700
Data Index: 1639722 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.8476. Min Act: -0.1700
Data Index: 6185966 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.8476. Min Act: -0.1700
Data Index: 7058226 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.7851. Min Act: -0.1700
Data Index: 75166 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.7226. Min Act: -0.1700
Data Index: 6185967 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.7226. Min Act: -0.1700
Data Index: 5734328 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6913. Min Act: -0.1700
Data Index: 1054035 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6913. Min Act: -0.1700
Data Index: 6928251 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6913. Min Act: -0.1700
Data Index: 3705428 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6601. Min Act: -0.1700
Data Index: 1700407 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6601. Min Act: -0.1700
Data Index: 4225830 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6601. Min Act: -0.1700
Data Index: 4252385 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6288. Min Act: -0.1700
Data Index: 6455096 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6601. Min Act: -0.1700
Data Index: 4993757 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6601. Min Act: -0.1700
Data Index: 2744339 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6913. Min Act: -0.1700
Data Index: 7058224 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6601. Min Act: -0.1700
Data Index: 163978 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6601. Min Act: -0.1700
Data Index: 3694634 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19