Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3788 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0965. Min Range: -6.0965
Max Act: 6.0965. Min Act: -0.1700
Data Index: 1716719 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0965. Min Range: -6.0965
Max Act: 5.7840. Min Act: -0.1700
Data Index: 8685878 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0965. Min Range: -6.0965
Max Act: 5.7215. Min Act: -0.1700
Data Index: 5380834 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0965. Min Range: -6.0965
Max Act: 5.6902. Min Act: -0.1700
Data Index: 971917 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0965. Min Range: -6.0965
Max Act: 5.6902. Min Act: -0.1700
Data Index: 3043434 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0965. Min Range: -6.0965
Max Act: 5.6590. Min Act: -0.1700
Data Index: 3190144 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0965. Min Range: -6.0965
Max Act: 5.6590. Min Act: -0.1700
Data Index: 548560 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0965. Min Range: -6.0965
Max Act: 5.5965. Min Act: -0.1700
Data Index: 1657313 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0965. Min Range: -6.0965
Max Act: 5.5965. Min Act: -0.1700
Data Index: 6848995 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0965. Min Range: -6.0965
Max Act: 5.5965. Min Act: -0.1700
Data Index: 2065061 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0965. Min Range: -6.0965
Max Act: 5.5652. Min Act: -0.1700
Data Index: 3663616 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0965. Min Range: -6.0965
Max Act: 5.5340. Min Act: -0.1700
Data Index: 7672181 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0965. Min Range: -6.0965
Max Act: 5.5027. Min Act: -0.1700
Data Index: 919620 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0965. Min Range: -6.0965
Max Act: 5.5027. Min Act: -0.1700
Data Index: 5625885 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0965. Min Range: -6.0965
Max Act: 5.4715. Min Act: -0.1700
Data Index: 1061991 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0965. Min Range: -6.0965
Max Act: 5.4715. Min Act: -0.1700
Data Index: 4635198 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0965. Min Range: -6.0965
Max Act: 5.4715. Min Act: -0.1700
Data Index: 2052104 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0965. Min Range: -6.0965
Max Act: 5.4715. Min Act: -0.1700
Data Index: 934951 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0965. Min Range: -6.0965
Max Act: 5.4402. Min Act: -0.1700
Data Index: 6984724 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0965. Min Range: -6.0965
Max Act: 5.4715. Min Act: -0.1700
Data Index: 5467896 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19