Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2594 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7413. Min Range: -7.7413
Max Act: 7.7413. Min Act: -0.1700
Data Index: 3120149 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7413. Min Range: -7.7413
Max Act: 7.6163. Min Act: -0.1700
Data Index: 2982921 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7413. Min Range: -7.7413
Max Act: 7.5850. Min Act: -0.1700
Data Index: 7170805 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7413. Min Range: -7.7413
Max Act: 7.5225. Min Act: -0.1700
Data Index: 4171234 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7413. Min Range: -7.7413
Max Act: 7.4913. Min Act: -0.1700
Data Index: 4633056 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7413. Min Range: -7.7413
Max Act: 7.4288. Min Act: -0.1700
Data Index: 7161524 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7413. Min Range: -7.7413
Max Act: 7.3975. Min Act: -0.1700
Data Index: 1850969 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7413. Min Range: -7.7413
Max Act: 7.3350. Min Act: -0.1700
Data Index: 6169757 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7413. Min Range: -7.7413
Max Act: 7.3038. Min Act: -0.1700
Data Index: 3089851 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7413. Min Range: -7.7413
Max Act: 7.3038. Min Act: -0.1700
Data Index: 5831198 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7413. Min Range: -7.7413
Max Act: 7.2725. Min Act: -0.1700
Data Index: 6925256 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7413. Min Range: -7.7413
Max Act: 7.2413. Min Act: -0.1700
Data Index: 5450915 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7413. Min Range: -7.7413
Max Act: 7.2413. Min Act: -0.1700
Data Index: 3826298 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7413. Min Range: -7.7413
Max Act: 7.2413. Min Act: -0.1700
Data Index: 3511893 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7413. Min Range: -7.7413
Max Act: 7.2100. Min Act: -0.1700
Data Index: 7114554 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7413. Min Range: -7.7413
Max Act: 7.2100. Min Act: -0.1700
Data Index: 5466520 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7413. Min Range: -7.7413
Max Act: 7.2100. Min Act: -0.1700
Data Index: 2968902 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7413. Min Range: -7.7413
Max Act: 7.2413. Min Act: -0.1700
Data Index: 6396931 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7413. Min Range: -7.7413
Max Act: 7.2413. Min Act: -0.1700
Data Index: 4188091 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7413. Min Range: -7.7413
Max Act: 7.1788. Min Act: -0.1700
Data Index: 4840929 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19