Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2673 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6988. Min Range: -7.6988
Max Act: 7.6988. Min Act: -0.1700
Data Index: 4964675 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6988. Min Range: -7.6988
Max Act: 7.4488. Min Act: -0.1700
Data Index: 3378284 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6988. Min Range: -7.6988
Max Act: 7.3863. Min Act: -0.1700
Data Index: 2600680 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6988. Min Range: -7.6988
Max Act: 7.2300. Min Act: -0.1700
Data Index: 3456085 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6988. Min Range: -7.6988
Max Act: 7.0738. Min Act: -0.1700
Data Index: 8514350 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6988. Min Range: -7.6988
Max Act: 6.9488. Min Act: -0.1700
Data Index: 6719269 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6988. Min Range: -7.6988
Max Act: 6.9488. Min Act: -0.1700
Data Index: 1433045 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6988. Min Range: -7.6988
Max Act: 6.9488. Min Act: -0.1700
Data Index: 2570660 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6988. Min Range: -7.6988
Max Act: 6.8863. Min Act: -0.1700
Data Index: 2506125 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6988. Min Range: -7.6988
Max Act: 6.8238. Min Act: -0.1700
Data Index: 3592123 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6988. Min Range: -7.6988
Max Act: 6.7613. Min Act: -0.1700
Data Index: 6155891 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6988. Min Range: -7.6988
Max Act: 6.7613. Min Act: -0.1700
Data Index: 5079844 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6988. Min Range: -7.6988
Max Act: 6.7925. Min Act: -0.1700
Data Index: 1257748 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6988. Min Range: -7.6988
Max Act: 6.7300. Min Act: -0.1700
Data Index: 8214333 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6988. Min Range: -7.6988
Max Act: 6.7613. Min Act: -0.1700
Data Index: 413791 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6988. Min Range: -7.6988
Max Act: 6.6675. Min Act: -0.1700
Data Index: 6406653 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6988. Min Range: -7.6988
Max Act: 6.6988. Min Act: -0.1700
Data Index: 3378279 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6988. Min Range: -7.6988
Max Act: 6.6675. Min Act: -0.1700
Data Index: 5148547 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6988. Min Range: -7.6988
Max Act: 6.6363. Min Act: -0.1700
Data Index: 8597382 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6988. Min Range: -7.6988
Max Act: 6.6363. Min Act: -0.1700
Data Index: 6857609 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19