Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3601 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9922. Min Range: -3.9922
Max Act: 3.9922. Min Act: -0.1700
Data Index: 6125325 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9922. Min Range: -3.9922
Max Act: 3.9922. Min Act: -0.1700
Data Index: 3342590 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9922. Min Range: -3.9922
Max Act: 3.9610. Min Act: -0.1700
Data Index: 4074207 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9922. Min Range: -3.9922
Max Act: 3.8516. Min Act: -0.1700
Data Index: 2377201 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9922. Min Range: -3.9922
Max Act: 3.8203. Min Act: -0.1700
Data Index: 4940144 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9922. Min Range: -3.9922
Max Act: 3.7734. Min Act: -0.1700
Data Index: 8820286 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9922. Min Range: -3.9922
Max Act: 3.7890. Min Act: -0.1700
Data Index: 7232654 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9922. Min Range: -3.9922
Max Act: 3.7890. Min Act: -0.1700
Data Index: 3654132 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9922. Min Range: -3.9922
Max Act: 3.7265. Min Act: -0.1700
Data Index: 3654131 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9922. Min Range: -3.9922
Max Act: 3.7421. Min Act: -0.1700
Data Index: 814041 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9922. Min Range: -3.9922
Max Act: 3.7108. Min Act: -0.1700
Data Index: 7539009 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9922. Min Range: -3.9922
Max Act: 3.7108. Min Act: -0.1700
Data Index: 4696811 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9922. Min Range: -3.9922
Max Act: 3.7108. Min Act: -0.1700
Data Index: 3723620 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9922. Min Range: -3.9922
Max Act: 3.7265. Min Act: -0.1700
Data Index: 2675839 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9922. Min Range: -3.9922
Max Act: 3.6952. Min Act: -0.1700
Data Index: 1160509 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9922. Min Range: -3.9922
Max Act: 3.6952. Min Act: -0.1700
Data Index: 5399107 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9922. Min Range: -3.9922
Max Act: 3.7108. Min Act: -0.1700
Data Index: 4984377 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9922. Min Range: -3.9922
Max Act: 3.6952. Min Act: -0.1700
Data Index: 292959 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9922. Min Range: -3.9922
Max Act: 3.7108. Min Act: -0.1700
Data Index: 2759452 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9922. Min Range: -3.9922
Max Act: 3.6639. Min Act: -0.1700
Data Index: 3514890 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19