Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3879 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7018. Min Range: -4.7018
Max Act: 4.7018. Min Act: -0.1700
Data Index: 6370092 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7018. Min Range: -4.7018
Max Act: 4.7018. Min Act: -0.1700
Data Index: 928780 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7018. Min Range: -4.7018
Max Act: 4.6081. Min Act: -0.1700
Data Index: 4471339 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7018. Min Range: -4.7018
Max Act: 4.6081. Min Act: -0.1700
Data Index: 8017319 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7018. Min Range: -4.7018
Max Act: 4.5768. Min Act: -0.1700
Data Index: 5871607 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7018. Min Range: -4.7018
Max Act: 4.5768. Min Act: -0.1700
Data Index: 8558518 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7018. Min Range: -4.7018
Max Act: 4.5456. Min Act: -0.1700
Data Index: 1716046 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7018. Min Range: -4.7018
Max Act: 4.5456. Min Act: -0.1700
Data Index: 3529870 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7018. Min Range: -4.7018
Max Act: 4.5456. Min Act: -0.1700
Data Index: 6592997 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7018. Min Range: -4.7018
Max Act: 4.4831. Min Act: -0.1700
Data Index: 5872076 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7018. Min Range: -4.7018
Max Act: 4.5143. Min Act: -0.1700
Data Index: 1385801 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7018. Min Range: -4.7018
Max Act: 4.4831. Min Act: -0.1700
Data Index: 5892671 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7018. Min Range: -4.7018
Max Act: 4.4831. Min Act: -0.1700
Data Index: 4263939 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7018. Min Range: -4.7018
Max Act: 4.4831. Min Act: -0.1700
Data Index: 6082998 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7018. Min Range: -4.7018
Max Act: 4.4518. Min Act: -0.1700
Data Index: 4157780 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7018. Min Range: -4.7018
Max Act: 4.4518. Min Act: -0.1700
Data Index: 4157781 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7018. Min Range: -4.7018
Max Act: 4.4518. Min Act: -0.1700
Data Index: 6531030 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7018. Min Range: -4.7018
Max Act: 4.4518. Min Act: -0.1700
Data Index: 4420939 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7018. Min Range: -4.7018
Max Act: 4.3893. Min Act: -0.1700
Data Index: 6860685 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7018. Min Range: -4.7018
Max Act: 4.4206. Min Act: -0.1700
Data Index: 6916882 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19