Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 895 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6637. Min Range: -6.6637
Max Act: 6.6637. Min Act: -0.1700
Data Index: 1618417 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6637. Min Range: -6.6637
Max Act: 6.5699. Min Act: -0.1700
Data Index: 144966 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6637. Min Range: -6.6637
Max Act: 6.5387. Min Act: -0.1700
Data Index: 5442153 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6637. Min Range: -6.6637
Max Act: 6.5074. Min Act: -0.1700
Data Index: 490462 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6637. Min Range: -6.6637
Max Act: 6.4762. Min Act: -0.1700
Data Index: 970681 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6637. Min Range: -6.6637
Max Act: 6.4137. Min Act: -0.1700
Data Index: 2136214 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6637. Min Range: -6.6637
Max Act: 6.4137. Min Act: -0.1700
Data Index: 4824651 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6637. Min Range: -6.6637
Max Act: 6.4137. Min Act: -0.1700
Data Index: 8176192 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6637. Min Range: -6.6637
Max Act: 6.2262. Min Act: -0.1700
Data Index: 2324964 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6637. Min Range: -6.6637
Max Act: 6.1949. Min Act: -0.1700
Data Index: 3617010 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6637. Min Range: -6.6637
Max Act: 6.1637. Min Act: -0.1700
Data Index: 311117 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6637. Min Range: -6.6637
Max Act: 6.1637. Min Act: -0.1700
Data Index: 5827788 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6637. Min Range: -6.6637
Max Act: 6.1324. Min Act: -0.1700
Data Index: 7323121 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6637. Min Range: -6.6637
Max Act: 6.1324. Min Act: -0.1700
Data Index: 3985605 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6637. Min Range: -6.6637
Max Act: 6.1324. Min Act: -0.1700
Data Index: 6578554 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6637. Min Range: -6.6637
Max Act: 6.1324. Min Act: -0.1700
Data Index: 5988791 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6637. Min Range: -6.6637
Max Act: 6.1012. Min Act: -0.1700
Data Index: 5965463 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6637. Min Range: -6.6637
Max Act: 6.1012. Min Act: -0.1700
Data Index: 6208331 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6637. Min Range: -6.6637
Max Act: 6.0699. Min Act: -0.1700
Data Index: 7533262 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6637. Min Range: -6.6637
Max Act: 6.0387. Min Act: -0.1700
Data Index: 3851959 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #19