Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2666 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0972. Min Range: -9.0972
Max Act: 9.0347. Min Act: -0.1700
Data Index: 4471412 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0972. Min Range: -9.0972
Max Act: 9.0972. Min Act: -0.1700
Data Index: 6664909 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0972. Min Range: -9.0972
Max Act: 8.9722. Min Act: -0.1700
Data Index: 2708699 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0972. Min Range: -9.0972
Max Act: 8.9097. Min Act: -0.1700
Data Index: 118953 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0972. Min Range: -9.0972
Max Act: 8.9097. Min Act: -0.1700
Data Index: 4769890 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0972. Min Range: -9.0972
Max Act: 8.8472. Min Act: -0.1700
Data Index: 6396948 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0972. Min Range: -9.0972
Max Act: 8.7847. Min Act: -0.1700
Data Index: 6357393 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0972. Min Range: -9.0972
Max Act: 8.7847. Min Act: -0.1700
Data Index: 1419384 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0972. Min Range: -9.0972
Max Act: 8.6597. Min Act: -0.1700
Data Index: 5413336 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0972. Min Range: -9.0972
Max Act: 8.6597. Min Act: -0.1700
Data Index: 1468121 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0972. Min Range: -9.0972
Max Act: 8.6597. Min Act: -0.1700
Data Index: 3627073 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0972. Min Range: -9.0972
Max Act: 8.5347. Min Act: -0.1700
Data Index: 756265 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0972. Min Range: -9.0972
Max Act: 8.5972. Min Act: -0.1700
Data Index: 6609534 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0972. Min Range: -9.0972
Max Act: 8.5972. Min Act: -0.1700
Data Index: 3425520 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0972. Min Range: -9.0972
Max Act: 8.5972. Min Act: -0.1700
Data Index: 5927190 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0972. Min Range: -9.0972
Max Act: 8.5347. Min Act: -0.1700
Data Index: 4426111 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0972. Min Range: -9.0972
Max Act: 8.4722. Min Act: -0.1700
Data Index: 47742 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0972. Min Range: -9.0972
Max Act: 8.4097. Min Act: -0.1700
Data Index: 2740575 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0972. Min Range: -9.0972
Max Act: 8.4722. Min Act: -0.1700
Data Index: 47357 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0972. Min Range: -9.0972
Max Act: 8.5347. Min Act: -0.1700
Data Index: 611974 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19