Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3780 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1070. Min Range: -4.1070
Max Act: 4.1070. Min Act: -0.1700
Data Index: 7953113 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1070. Min Range: -4.1070
Max Act: 4.0445. Min Act: -0.1700
Data Index: 7155701 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1070. Min Range: -4.1070
Max Act: 4.0445. Min Act: -0.1700
Data Index: 8252796 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1070. Min Range: -4.1070
Max Act: 3.9820. Min Act: -0.1700
Data Index: 8821281 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1070. Min Range: -4.1070
Max Act: 4.0133. Min Act: -0.1700
Data Index: 4528909 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1070. Min Range: -4.1070
Max Act: 3.9820. Min Act: -0.1700
Data Index: 831775 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1070. Min Range: -4.1070
Max Act: 3.9195. Min Act: -0.1700
Data Index: 4383184 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1070. Min Range: -4.1070
Max Act: 3.8882. Min Act: -0.1700
Data Index: 325708 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1070. Min Range: -4.1070
Max Act: 3.8882. Min Act: -0.1700
Data Index: 3485852 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1070. Min Range: -4.1070
Max Act: 3.8413. Min Act: -0.1700
Data Index: 7862144 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1070. Min Range: -4.1070
Max Act: 3.8726. Min Act: -0.1700
Data Index: 370465 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1070. Min Range: -4.1070
Max Act: 3.8413. Min Act: -0.1700
Data Index: 3658595 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1070. Min Range: -4.1070
Max Act: 3.8100. Min Act: -0.1700
Data Index: 7063948 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1070. Min Range: -4.1070
Max Act: 3.7944. Min Act: -0.1700
Data Index: 7631826 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1070. Min Range: -4.1070
Max Act: 3.7788. Min Act: -0.1700
Data Index: 5801350 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1070. Min Range: -4.1070
Max Act: 3.7788. Min Act: -0.1700
Data Index: 3829994 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1070. Min Range: -4.1070
Max Act: 3.7788. Min Act: -0.1700
Data Index: 5732353 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1070. Min Range: -4.1070
Max Act: 3.7788. Min Act: -0.1700
Data Index: 1999383 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1070. Min Range: -4.1070
Max Act: 3.7005. Min Act: -0.1700
Data Index: 827413 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1070. Min Range: -4.1070
Max Act: 3.7162. Min Act: -0.1700
Data Index: 7810166 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19