Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 608 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7927. Min Range: -3.7927
Max Act: 3.7927. Min Act: -0.1700
Data Index: 1850769 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7927. Min Range: -3.7927
Max Act: 3.7302. Min Act: -0.1700
Data Index: 7972669 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7927. Min Range: -3.7927
Max Act: 3.7614. Min Act: -0.1700
Data Index: 979572 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7927. Min Range: -3.7927
Max Act: 3.7302. Min Act: -0.1700
Data Index: 5165976 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7927. Min Range: -3.7927
Max Act: 3.6989. Min Act: -0.1700
Data Index: 2839130 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7927. Min Range: -3.7927
Max Act: 3.6989. Min Act: -0.1700
Data Index: 836675 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7927. Min Range: -3.7927
Max Act: 3.6989. Min Act: -0.1700
Data Index: 5048841 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7927. Min Range: -3.7927
Max Act: 3.6832. Min Act: -0.1700
Data Index: 1190638 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7927. Min Range: -3.7927
Max Act: 3.6676. Min Act: -0.1700
Data Index: 2620234 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7927. Min Range: -3.7927
Max Act: 3.6363. Min Act: -0.1700
Data Index: 6038330 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7927. Min Range: -3.7927
Max Act: 3.6050. Min Act: -0.1700
Data Index: 237005 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7927. Min Range: -3.7927
Max Act: 3.6206. Min Act: -0.1700
Data Index: 1898826 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7927. Min Range: -3.7927
Max Act: 3.6206. Min Act: -0.1700
Data Index: 5361215 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7927. Min Range: -3.7927
Max Act: 3.6050. Min Act: -0.1700
Data Index: 3805843 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7927. Min Range: -3.7927
Max Act: 3.6050. Min Act: -0.1700
Data Index: 847787 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7927. Min Range: -3.7927
Max Act: 3.6206. Min Act: -0.1700
Data Index: 1581386 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7927. Min Range: -3.7927
Max Act: 3.5893. Min Act: -0.1700
Data Index: 8173890 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7927. Min Range: -3.7927
Max Act: 3.5580. Min Act: -0.1700
Data Index: 5267527 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7927. Min Range: -3.7927
Max Act: 3.5424. Min Act: -0.1700
Data Index: 5098324 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7927. Min Range: -3.7927
Max Act: 3.5580. Min Act: -0.1700
Data Index: 7308933 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19