Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2940 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3498. Min Range: -4.3498
Max Act: 4.3498. Min Act: -0.1700
Data Index: 1899068 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3498. Min Range: -4.3498
Max Act: 4.2873. Min Act: -0.1700
Data Index: 8249026 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3498. Min Range: -4.3498
Max Act: 4.1311. Min Act: -0.1700
Data Index: 380333 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3498. Min Range: -4.3498
Max Act: 4.0373. Min Act: -0.1700
Data Index: 2959506 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3498. Min Range: -4.3498
Max Act: 4.0060. Min Act: -0.1700
Data Index: 7149365 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3498. Min Range: -4.3498
Max Act: 4.0060. Min Act: -0.1700
Data Index: 6336167 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3498. Min Range: -4.3498
Max Act: 3.9435. Min Act: -0.1700
Data Index: 6949854 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3498. Min Range: -4.3498
Max Act: 3.9122. Min Act: -0.1700
Data Index: 4982251 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3498. Min Range: -4.3498
Max Act: 3.9122. Min Act: -0.1700
Data Index: 1706542 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3498. Min Range: -4.3498
Max Act: 3.9122. Min Act: -0.1700
Data Index: 4683649 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3498. Min Range: -4.3498
Max Act: 3.9122. Min Act: -0.1700
Data Index: 2740022 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3498. Min Range: -4.3498
Max Act: 3.8810. Min Act: -0.1700
Data Index: 2431044 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3498. Min Range: -4.3498
Max Act: 3.8497. Min Act: -0.1700
Data Index: 8249025 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3498. Min Range: -4.3498
Max Act: 3.8497. Min Act: -0.1700
Data Index: 4516784 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3498. Min Range: -4.3498
Max Act: 3.8497. Min Act: -0.1700
Data Index: 6175570 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3498. Min Range: -4.3498
Max Act: 3.8184. Min Act: -0.1700
Data Index: 7915745 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3498. Min Range: -4.3498
Max Act: 3.8184. Min Act: -0.1700
Data Index: 7601128 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3498. Min Range: -4.3498
Max Act: 3.8184. Min Act: -0.1700
Data Index: 5664317 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3498. Min Range: -4.3498
Max Act: 3.8184. Min Act: -0.1700
Data Index: 4007192 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3498. Min Range: -4.3498
Max Act: 3.8184. Min Act: -0.1700
Data Index: 8613979 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19