Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2702 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4929. Min Range: -5.4929
Max Act: 5.4929. Min Act: -0.1700
Data Index: 1690472 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4929. Min Range: -5.4929
Max Act: 5.3992. Min Act: -0.1700
Data Index: 8507599 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4929. Min Range: -5.4929
Max Act: 5.3679. Min Act: -0.1700
Data Index: 4740992 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4929. Min Range: -5.4929
Max Act: 5.2742. Min Act: -0.1700
Data Index: 8500451 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4929. Min Range: -5.4929
Max Act: 5.2117. Min Act: -0.1700
Data Index: 308779 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4929. Min Range: -5.4929
Max Act: 5.2117. Min Act: -0.1700
Data Index: 8786634 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4929. Min Range: -5.4929
Max Act: 5.2117. Min Act: -0.1700
Data Index: 5347873 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4929. Min Range: -5.4929
Max Act: 5.1804. Min Act: -0.1700
Data Index: 475124 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4929. Min Range: -5.4929
Max Act: 5.1804. Min Act: -0.1700
Data Index: 8032514 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4929. Min Range: -5.4929
Max Act: 5.1492. Min Act: -0.1700
Data Index: 8333663 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4929. Min Range: -5.4929
Max Act: 5.1179. Min Act: -0.1700
Data Index: 7499920 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4929. Min Range: -5.4929
Max Act: 5.1804. Min Act: -0.1700
Data Index: 7793708 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4929. Min Range: -5.4929
Max Act: 5.1179. Min Act: -0.1700
Data Index: 5375497 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4929. Min Range: -5.4929
Max Act: 5.0867. Min Act: -0.1700
Data Index: 3319768 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4929. Min Range: -5.4929
Max Act: 5.0554. Min Act: -0.1700
Data Index: 4904208 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4929. Min Range: -5.4929
Max Act: 5.0554. Min Act: -0.1700
Data Index: 7865962 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4929. Min Range: -5.4929
Max Act: 5.0867. Min Act: -0.1700
Data Index: 6127241 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4929. Min Range: -5.4929
Max Act: 5.0242. Min Act: -0.1700
Data Index: 5293375 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4929. Min Range: -5.4929
Max Act: 4.9929. Min Act: -0.1700
Data Index: 6933426 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4929. Min Range: -5.4929
Max Act: 4.9929. Min Act: -0.1700
Data Index: 5976727 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19