Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5523 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.7092. Min Act: -0.1700
Data Index: 1167060 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.2404. Min Act: -0.1700
Data Index: 6336326 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.1467. Min Act: -0.1700
Data Index: 5031738 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.1467. Min Act: -0.1700
Data Index: 89 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.1154. Min Act: -0.1700
Data Index: 6631949 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.0842. Min Act: -0.1700
Data Index: 3282630 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.0842. Min Act: -0.1700
Data Index: 7093840 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.0842. Min Act: -0.1700
Data Index: 3456543 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.0529. Min Act: -0.1700
Data Index: 1761759 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.0529. Min Act: -0.1700
Data Index: 8730447 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.0529. Min Act: -0.1700
Data Index: 6070816 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.0842. Min Act: -0.1700
Data Index: 5528417 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.0217. Min Act: -0.1700
Data Index: 4740086 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7092. Min Range: -6.7092
Max Act: 5.9592. Min Act: -0.1700
Data Index: 6939451 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7092. Min Range: -6.7092
Max Act: 5.9904. Min Act: -0.1700
Data Index: 852810 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7092. Min Range: -6.7092
Max Act: 5.9592. Min Act: -0.1700
Data Index: 2256321 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7092. Min Range: -6.7092
Max Act: 5.9904. Min Act: -0.1700
Data Index: 4711753 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7092. Min Range: -6.7092
Max Act: 5.9592. Min Act: -0.1700
Data Index: 327859 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7092. Min Range: -6.7092
Max Act: 5.9279. Min Act: -0.1700
Data Index: 3498514 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7092. Min Range: -6.7092
Max Act: 5.9279. Min Act: -0.1700
Data Index: 6421035 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19