Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3090 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6705. Min Range: -8.6705
Max Act: 8.6705. Min Act: -0.1700
Data Index: 3875287 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6705. Min Range: -8.6705
Max Act: 8.6080. Min Act: -0.1700
Data Index: 3325542 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6705. Min Range: -8.6705
Max Act: 8.4830. Min Act: -0.1700
Data Index: 7694919 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6705. Min Range: -8.6705
Max Act: 8.3580. Min Act: -0.1700
Data Index: 3637366 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6705. Min Range: -8.6705
Max Act: 8.2955. Min Act: -0.1700
Data Index: 162938 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6705. Min Range: -8.6705
Max Act: 8.1705. Min Act: -0.1700
Data Index: 7431860 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6705. Min Range: -8.6705
Max Act: 8.1705. Min Act: -0.1700
Data Index: 4922154 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6705. Min Range: -8.6705
Max Act: 8.1705. Min Act: -0.1700
Data Index: 4488484 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6705. Min Range: -8.6705
Max Act: 8.1705. Min Act: -0.1700
Data Index: 2767470 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6705. Min Range: -8.6705
Max Act: 8.1705. Min Act: -0.1700
Data Index: 4791143 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6705. Min Range: -8.6705
Max Act: 8.1705. Min Act: -0.1700
Data Index: 6054039 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6705. Min Range: -8.6705
Max Act: 8.1080. Min Act: -0.1700
Data Index: 4893065 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6705. Min Range: -8.6705
Max Act: 8.0455. Min Act: -0.1700
Data Index: 7524349 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6705. Min Range: -8.6705
Max Act: 8.0455. Min Act: -0.1700
Data Index: 7194350 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6705. Min Range: -8.6705
Max Act: 7.9830. Min Act: -0.1700
Data Index: 1653751 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6705. Min Range: -8.6705
Max Act: 7.9830. Min Act: -0.1700
Data Index: 6356280 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6705. Min Range: -8.6705
Max Act: 7.9830. Min Act: -0.1700
Data Index: 69846 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6705. Min Range: -8.6705
Max Act: 7.9830. Min Act: -0.1700
Data Index: 3157762 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6705. Min Range: -8.6705
Max Act: 7.9830. Min Act: -0.1700
Data Index: 3828641 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6705. Min Range: -8.6705
Max Act: 7.9205. Min Act: -0.1700
Data Index: 7785785 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19