Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6396 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6060. Min Range: -3.6060
Max Act: 3.6060. Min Act: -0.1700
Data Index: 8521122 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6060. Min Range: -3.6060
Max Act: 3.6060. Min Act: -0.1700
Data Index: 8454563 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6060. Min Range: -3.6060
Max Act: 3.5747. Min Act: -0.1698
Data Index: 1701 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6060. Min Range: -3.6060
Max Act: 3.5121. Min Act: -0.1700
Data Index: 5619932 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6060. Min Range: -3.6060
Max Act: 3.5121. Min Act: -0.1700
Data Index: 2669283 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6060. Min Range: -3.6060
Max Act: 3.5121. Min Act: -0.1685
Data Index: 623879 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6060. Min Range: -3.6060
Max Act: 3.5121. Min Act: -0.1669
Data Index: 2550722 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6060. Min Range: -3.6060
Max Act: 3.5121. Min Act: -0.1539
Data Index: 2310409 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6060. Min Range: -3.6060
Max Act: 3.5121. Min Act: -0.1562
Data Index: 4755598 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6060. Min Range: -3.6060
Max Act: 3.5121. Min Act: -0.1697
Data Index: 1943600 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6060. Min Range: -3.6060
Max Act: 3.5121. Min Act: -0.1700
Data Index: 6414745 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6060. Min Range: -3.6060
Max Act: 3.5121. Min Act: -0.1699
Data Index: 3937548 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6060. Min Range: -3.6060
Max Act: 3.5121. Min Act: -0.1684
Data Index: 2748108 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6060. Min Range: -3.6060
Max Act: 3.5121. Min Act: -0.1700
Data Index: 3445156 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6060. Min Range: -3.6060
Max Act: 3.5121. Min Act: -0.1700
Data Index: 6464114 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6060. Min Range: -3.6060
Max Act: 3.4808. Min Act: -0.1479
Data Index: 8588482 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6060. Min Range: -3.6060
Max Act: 3.4808. Min Act: -0.1700
Data Index: 8267990 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6060. Min Range: -3.6060
Max Act: 3.4494. Min Act: -0.1677
Data Index: 8782417 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6060. Min Range: -3.6060
Max Act: 3.4494. Min Act: -0.1700
Data Index: 5294946 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6060. Min Range: -3.6060
Max Act: 3.4494. Min Act: -0.1683
Data Index: 3253221 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19