Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 84 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2472. Min Range: -6.2472
Max Act: 6.2472. Min Act: -0.1700
Data Index: 2892963 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2472. Min Range: -6.2472
Max Act: 6.1535. Min Act: -0.1700
Data Index: 1369321 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2472. Min Range: -6.2472
Max Act: 6.1535. Min Act: -0.1700
Data Index: 2892962 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2472. Min Range: -6.2472
Max Act: 6.1535. Min Act: -0.1700
Data Index: 2132704 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2472. Min Range: -6.2472
Max Act: 6.0285. Min Act: -0.1698
Data Index: 956596 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2472. Min Range: -6.2472
Max Act: 5.9347. Min Act: -0.1700
Data Index: 6420109 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2472. Min Range: -6.2472
Max Act: 5.9035. Min Act: -0.1700
Data Index: 5091837 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2472. Min Range: -6.2472
Max Act: 5.8722. Min Act: -0.1700
Data Index: 1521296 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2472. Min Range: -6.2472
Max Act: 5.8410. Min Act: -0.1700
Data Index: 8142757 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2472. Min Range: -6.2472
Max Act: 5.8097. Min Act: -0.1700
Data Index: 1622910 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2472. Min Range: -6.2472
Max Act: 5.8097. Min Act: -0.1700
Data Index: 6204327 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2472. Min Range: -6.2472
Max Act: 5.8410. Min Act: -0.1700
Data Index: 6627657 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2472. Min Range: -6.2472
Max Act: 5.8097. Min Act: -0.1700
Data Index: 1577160 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2472. Min Range: -6.2472
Max Act: 5.7785. Min Act: -0.1700
Data Index: 2893430 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2472. Min Range: -6.2472
Max Act: 5.7785. Min Act: -0.1700
Data Index: 7986426 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2472. Min Range: -6.2472
Max Act: 5.7472. Min Act: -0.1700
Data Index: 4216491 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2472. Min Range: -6.2472
Max Act: 5.7472. Min Act: -0.1700
Data Index: 6403965 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2472. Min Range: -6.2472
Max Act: 5.7472. Min Act: -0.1700
Data Index: 5915818 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2472. Min Range: -6.2472
Max Act: 5.7472. Min Act: -0.1700
Data Index: 8258841 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2472. Min Range: -6.2472
Max Act: 5.7472. Min Act: -0.1700
Data Index: 1582390 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19