Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3420 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4791. Min Range: -5.4791
Max Act: 5.4791. Min Act: -0.1700
Data Index: 6858727 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4791. Min Range: -5.4791
Max Act: 5.2603. Min Act: -0.1700
Data Index: 2757177 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4791. Min Range: -5.4791
Max Act: 5.1353. Min Act: -0.1700
Data Index: 4089174 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4791. Min Range: -5.4791
Max Act: 5.1353. Min Act: -0.1700
Data Index: 1309208 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4791. Min Range: -5.4791
Max Act: 5.1041. Min Act: -0.1700
Data Index: 1004927 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4791. Min Range: -5.4791
Max Act: 5.0728. Min Act: -0.1700
Data Index: 2325965 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4791. Min Range: -5.4791
Max Act: 5.0103. Min Act: -0.1700
Data Index: 5335188 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4791. Min Range: -5.4791
Max Act: 5.0103. Min Act: -0.1700
Data Index: 7382580 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4791. Min Range: -5.4791
Max Act: 5.0103. Min Act: -0.1700
Data Index: 1692971 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4791. Min Range: -5.4791
Max Act: 4.9791. Min Act: -0.1700
Data Index: 6671882 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4791. Min Range: -5.4791
Max Act: 4.9478. Min Act: -0.1700
Data Index: 1296762 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4791. Min Range: -5.4791
Max Act: 4.9166. Min Act: -0.1700
Data Index: 5654863 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4791. Min Range: -5.4791
Max Act: 4.8541. Min Act: -0.1700
Data Index: 4831386 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4791. Min Range: -5.4791
Max Act: 4.8541. Min Act: -0.1700
Data Index: 991019 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4791. Min Range: -5.4791
Max Act: 4.8228. Min Act: -0.1700
Data Index: 800071 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4791. Min Range: -5.4791
Max Act: 4.8228. Min Act: -0.1700
Data Index: 6893920 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4791. Min Range: -5.4791
Max Act: 4.7603. Min Act: -0.1700
Data Index: 1018839 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4791. Min Range: -5.4791
Max Act: 4.7916. Min Act: -0.1700
Data Index: 6333868 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4791. Min Range: -5.4791
Max Act: 4.7916. Min Act: -0.1700
Data Index: 248797 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4791. Min Range: -5.4791
Max Act: 4.7603. Min Act: -0.1700
Data Index: 1667781 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19