Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3049 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6318. Min Range: -3.6318
Max Act: 3.6318. Min Act: -0.1700
Data Index: 7810820 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6318. Min Range: -3.6318
Max Act: 3.6005. Min Act: -0.1700
Data Index: 4565588 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6318. Min Range: -3.6318
Max Act: 3.6005. Min Act: -0.1700
Data Index: 8323672 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6318. Min Range: -3.6318
Max Act: 3.6005. Min Act: -0.1700
Data Index: 3132361 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6318. Min Range: -3.6318
Max Act: 3.6005. Min Act: -0.1700
Data Index: 2373041 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6318. Min Range: -3.6318
Max Act: 3.5692. Min Act: -0.1700
Data Index: 8411756 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6318. Min Range: -3.6318
Max Act: 3.5692. Min Act: -0.1700
Data Index: 2570515 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6318. Min Range: -3.6318
Max Act: 3.5692. Min Act: -0.1700
Data Index: 3089761 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6318. Min Range: -3.6318
Max Act: 3.6005. Min Act: -0.1700
Data Index: 4362401 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6318. Min Range: -3.6318
Max Act: 3.5692. Min Act: -0.1700
Data Index: 8675829 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6318. Min Range: -3.6318
Max Act: 3.5692. Min Act: -0.1700
Data Index: 8604198 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6318. Min Range: -3.6318
Max Act: 3.5692. Min Act: -0.1700
Data Index: 2094156 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6318. Min Range: -3.6318
Max Act: 3.5378. Min Act: -0.1700
Data Index: 972536 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6318. Min Range: -3.6318
Max Act: 3.5378. Min Act: -0.1700
Data Index: 436082 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6318. Min Range: -3.6318
Max Act: 3.5378. Min Act: -0.1700
Data Index: 4251069 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6318. Min Range: -3.6318
Max Act: 3.5692. Min Act: -0.1700
Data Index: 5325906 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6318. Min Range: -3.6318
Max Act: 3.5378. Min Act: -0.1700
Data Index: 4491688 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6318. Min Range: -3.6318
Max Act: 3.5065. Min Act: -0.1700
Data Index: 3094371 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6318. Min Range: -3.6318
Max Act: 3.5065. Min Act: -0.1700
Data Index: 5492133 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6318. Min Range: -3.6318
Max Act: 3.5065. Min Act: -0.1700
Data Index: 5914918 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19