Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1621. Min Range: -3.1621
Max Act: 3.1621. Min Act: -0.1661
Data Index: 3737284 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1621. Min Range: -3.1621
Max Act: 3.1306. Min Act: -0.1667
Data Index: 8626113 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1621. Min Range: -3.1621
Max Act: 3.1306. Min Act: -0.1689
Data Index: 7908953 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1621. Min Range: -3.1621
Max Act: 3.1306. Min Act: -0.1699
Data Index: 776625 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1621. Min Range: -3.1621
Max Act: 3.1306. Min Act: -0.1699
Data Index: 5553219 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1621. Min Range: -3.1621
Max Act: 3.0676. Min Act: -0.1691
Data Index: 3040224 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1621. Min Range: -3.1621
Max Act: 3.0676. Min Act: -0.1698
Data Index: 6575980 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1621. Min Range: -3.1621
Max Act: 3.0360. Min Act: -0.1699
Data Index: 1042027 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1621. Min Range: -3.1621
Max Act: 3.0360. Min Act: -0.1698
Data Index: 7702435 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1621. Min Range: -3.1621
Max Act: 3.0360. Min Act: -0.1700
Data Index: 4961535 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1621. Min Range: -3.1621
Max Act: 3.0045. Min Act: -0.1700
Data Index: 7197748 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1621. Min Range: -3.1621
Max Act: 3.0045. Min Act: -0.1671
Data Index: 2492277 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1621. Min Range: -3.1621
Max Act: 3.0045. Min Act: -0.1700
Data Index: 4744148 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1621. Min Range: -3.1621
Max Act: 3.0045. Min Act: -0.1700
Data Index: 8669517 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1621. Min Range: -3.1621
Max Act: 2.9728. Min Act: -0.1700
Data Index: 3151849 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1621. Min Range: -3.1621
Max Act: 2.9728. Min Act: -0.1699
Data Index: 489746 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1621. Min Range: -3.1621
Max Act: 2.9728. Min Act: -0.1539
Data Index: 1503437 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1621. Min Range: -3.1621
Max Act: 2.9728. Min Act: -0.1655
Data Index: 5916008 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1621. Min Range: -3.1621
Max Act: 2.9728. Min Act: -0.1700
Data Index: 6256311 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1621. Min Range: -3.1621
Max Act: 2.9728. Min Act: -0.1698
Data Index: 6425677 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19