Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5331 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4095. Min Range: -3.4095
Max Act: 3.4095. Min Act: -0.1700
Data Index: 48939 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4095. Min Range: -3.4095
Max Act: 3.1425. Min Act: -0.1700
Data Index: 5321671 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4095. Min Range: -3.4095
Max Act: 3.1110. Min Act: -0.1700
Data Index: 6388751 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4095. Min Range: -3.4095
Max Act: 3.0953. Min Act: -0.1700
Data Index: 3366483 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4095. Min Range: -3.4095
Max Act: 3.0795. Min Act: -0.1700
Data Index: 6539824 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4095. Min Range: -3.4095
Max Act: 3.0795. Min Act: -0.1700
Data Index: 2295256 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4095. Min Range: -3.4095
Max Act: 3.0637. Min Act: -0.1700
Data Index: 3997681 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4095. Min Range: -3.4095
Max Act: 3.0479. Min Act: -0.1700
Data Index: 6131695 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4095. Min Range: -3.4095
Max Act: 3.0637. Min Act: -0.1700
Data Index: 6539831 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4095. Min Range: -3.4095
Max Act: 3.0322. Min Act: -0.1700
Data Index: 1998524 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4095. Min Range: -3.4095
Max Act: 3.0322. Min Act: -0.1700
Data Index: 8082836 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4095. Min Range: -3.4095
Max Act: 3.0322. Min Act: -0.1700
Data Index: 4161794 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4095. Min Range: -3.4095
Max Act: 3.0164. Min Act: -0.1700
Data Index: 2106377 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4095. Min Range: -3.4095
Max Act: 3.0322. Min Act: -0.1700
Data Index: 6539821 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4095. Min Range: -3.4095
Max Act: 3.0164. Min Act: -0.1700
Data Index: 1505514 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4095. Min Range: -3.4095
Max Act: 3.0164. Min Act: -0.1700
Data Index: 5406308 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4095. Min Range: -3.4095
Max Act: 3.0006. Min Act: -0.1700
Data Index: 6023017 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4095. Min Range: -3.4095
Max Act: 3.0006. Min Act: -0.1700
Data Index: 2410792 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4095. Min Range: -3.4095
Max Act: 3.0006. Min Act: -0.1700
Data Index: 7260244 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4095. Min Range: -3.4095
Max Act: 2.9848. Min Act: -0.1698
Data Index: 5118066 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19