Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3076 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1690. Min Range: -2.1690
Max Act: 2.1690. Min Act: -0.1697
Data Index: 839413 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1690. Min Range: -2.1690
Max Act: 2.1607. Min Act: -0.1698
Data Index: 1411432 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1690. Min Range: -2.1690
Max Act: 2.1524. Min Act: -0.1700
Data Index: 7343681 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1690. Min Range: -2.1690
Max Act: 2.1524. Min Act: -0.1699
Data Index: 1566423 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1690. Min Range: -2.1690
Max Act: 2.1524. Min Act: -0.1700
Data Index: 5599261 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1690. Min Range: -2.1690
Max Act: 2.1441. Min Act: -0.1700
Data Index: 4931060 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1690. Min Range: -2.1690
Max Act: 2.1357. Min Act: -0.1696
Data Index: 6281134 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1690. Min Range: -2.1690
Max Act: 2.1274. Min Act: -0.1700
Data Index: 1272808 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1690. Min Range: -2.1690
Max Act: 2.1107. Min Act: -0.1690
Data Index: 332127 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1690. Min Range: -2.1690
Max Act: 2.1107. Min Act: -0.1658
Data Index: 8312616 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1690. Min Range: -2.1690
Max Act: 2.1023. Min Act: -0.1700
Data Index: 3071186 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1690. Min Range: -2.1690
Max Act: 2.0939. Min Act: -0.1700
Data Index: 5102446 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1690. Min Range: -2.1690
Max Act: 2.0939. Min Act: -0.1638
Data Index: 8436832 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1690. Min Range: -2.1690
Max Act: 2.0939. Min Act: -0.1700
Data Index: 1379454 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1690. Min Range: -2.1690
Max Act: 2.0855. Min Act: -0.1700
Data Index: 6800318 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1690. Min Range: -2.1690
Max Act: 2.0688. Min Act: -0.1700
Data Index: 1609045 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1690. Min Range: -2.1690
Max Act: 2.0771. Min Act: -0.1700
Data Index: 4000024 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1690. Min Range: -2.1690
Max Act: 2.0688. Min Act: -0.1699
Data Index: 5717461 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1690. Min Range: -2.1690
Max Act: 2.0688. Min Act: -0.1696
Data Index: 2198670 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1690. Min Range: -2.1690
Max Act: 2.0604. Min Act: -0.1698
Data Index: 6949685 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19