Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3252 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0519. Min Range: -8.0519
Max Act: 8.0519. Min Act: -0.1700
Data Index: 3505979 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0519. Min Range: -8.0519
Max Act: 7.9269. Min Act: -0.1700
Data Index: 4254472 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0519. Min Range: -8.0519
Max Act: 7.8956. Min Act: -0.1700
Data Index: 5547056 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0519. Min Range: -8.0519
Max Act: 7.8644. Min Act: -0.1700
Data Index: 4111426 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0519. Min Range: -8.0519
Max Act: 7.8019. Min Act: -0.1700
Data Index: 2970663 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0519. Min Range: -8.0519
Max Act: 7.8019. Min Act: -0.1700
Data Index: 5520420 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0519. Min Range: -8.0519
Max Act: 7.8019. Min Act: -0.1700
Data Index: 7728645 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0519. Min Range: -8.0519
Max Act: 7.7706. Min Act: -0.1700
Data Index: 6976867 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0519. Min Range: -8.0519
Max Act: 7.7706. Min Act: -0.1700
Data Index: 8387524 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0519. Min Range: -8.0519
Max Act: 7.7394. Min Act: -0.1700
Data Index: 3727660 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0519. Min Range: -8.0519
Max Act: 7.7706. Min Act: -0.1700
Data Index: 1481526 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0519. Min Range: -8.0519
Max Act: 7.7706. Min Act: -0.1700
Data Index: 2354149 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0519. Min Range: -8.0519
Max Act: 7.7081. Min Act: -0.1700
Data Index: 2545148 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0519. Min Range: -8.0519
Max Act: 7.7081. Min Act: -0.1700
Data Index: 7380054 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0519. Min Range: -8.0519
Max Act: 7.7394. Min Act: -0.1700
Data Index: 7528187 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0519. Min Range: -8.0519
Max Act: 7.7394. Min Act: -0.1700
Data Index: 2847481 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0519. Min Range: -8.0519
Max Act: 7.7394. Min Act: -0.1700
Data Index: 3260344 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0519. Min Range: -8.0519
Max Act: 7.7081. Min Act: -0.1700
Data Index: 2838059 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0519. Min Range: -8.0519
Max Act: 7.7081. Min Act: -0.1700
Data Index: 564940 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0519. Min Range: -8.0519
Max Act: 7.6769. Min Act: -0.1700
Data Index: 1929574 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19