Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1917 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6059. Min Range: -7.6059
Max Act: 7.6059. Min Act: -0.1700
Data Index: 1405756 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6059. Min Range: -7.6059
Max Act: 7.2934. Min Act: -0.1700
Data Index: 746554 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6059. Min Range: -7.6059
Max Act: 7.2621. Min Act: -0.1700
Data Index: 6706710 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6059. Min Range: -7.6059
Max Act: 7.0434. Min Act: -0.1700
Data Index: 2783770 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6059. Min Range: -7.6059
Max Act: 7.0434. Min Act: -0.1700
Data Index: 1959728 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6059. Min Range: -7.6059
Max Act: 7.0121. Min Act: -0.1700
Data Index: 6557937 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6059. Min Range: -7.6059
Max Act: 7.0121. Min Act: -0.1700
Data Index: 8190320 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6059. Min Range: -7.6059
Max Act: 7.0121. Min Act: -0.1700
Data Index: 3130651 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6059. Min Range: -7.6059
Max Act: 6.9809. Min Act: -0.1700
Data Index: 693546 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6059. Min Range: -7.6059
Max Act: 6.9809. Min Act: -0.1700
Data Index: 695719 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6059. Min Range: -7.6059
Max Act: 6.9809. Min Act: -0.1700
Data Index: 7555581 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6059. Min Range: -7.6059
Max Act: 6.9809. Min Act: -0.1700
Data Index: 5696478 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6059. Min Range: -7.6059
Max Act: 6.9496. Min Act: -0.1700
Data Index: 1731370 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6059. Min Range: -7.6059
Max Act: 6.9496. Min Act: -0.1700
Data Index: 7813611 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6059. Min Range: -7.6059
Max Act: 6.9184. Min Act: -0.1700
Data Index: 1717426 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6059. Min Range: -7.6059
Max Act: 6.9184. Min Act: -0.1700
Data Index: 2658505 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6059. Min Range: -7.6059
Max Act: 6.9184. Min Act: -0.1700
Data Index: 7097583 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6059. Min Range: -7.6059
Max Act: 6.9184. Min Act: -0.1700
Data Index: 1945221 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6059. Min Range: -7.6059
Max Act: 6.9184. Min Act: -0.1700
Data Index: 2591732 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6059. Min Range: -7.6059
Max Act: 6.9184. Min Act: -0.1700
Data Index: 4430173 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19