Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5187 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1624. Min Range: -8.1624
Max Act: 8.1624. Min Act: -0.1700
Data Index: 1796529 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1624. Min Range: -8.1624
Max Act: 8.0999. Min Act: -0.1700
Data Index: 4127445 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1624. Min Range: -8.1624
Max Act: 7.9749. Min Act: -0.1700
Data Index: 2751037 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1624. Min Range: -8.1624
Max Act: 7.9437. Min Act: -0.1700
Data Index: 4737258 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1624. Min Range: -8.1624
Max Act: 7.8499. Min Act: -0.1700
Data Index: 580338 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1624. Min Range: -8.1624
Max Act: 7.8499. Min Act: -0.1700
Data Index: 5307274 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1624. Min Range: -8.1624
Max Act: 7.7874. Min Act: -0.1700
Data Index: 416114 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1624. Min Range: -8.1624
Max Act: 7.8187. Min Act: -0.1700
Data Index: 2169170 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1624. Min Range: -8.1624
Max Act: 7.7249. Min Act: -0.1700
Data Index: 74381 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1624. Min Range: -8.1624
Max Act: 7.6624. Min Act: -0.1700
Data Index: 5715638 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1624. Min Range: -8.1624
Max Act: 7.6937. Min Act: -0.1700
Data Index: 6582228 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1624. Min Range: -8.1624
Max Act: 7.6624. Min Act: -0.1700
Data Index: 2182942 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1624. Min Range: -8.1624
Max Act: 7.6312. Min Act: -0.1700
Data Index: 2979928 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1624. Min Range: -8.1624
Max Act: 7.5999. Min Act: -0.1700
Data Index: 1811814 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1624. Min Range: -8.1624
Max Act: 7.6312. Min Act: -0.1700
Data Index: 6632147 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1624. Min Range: -8.1624
Max Act: 7.5999. Min Act: -0.1700
Data Index: 4518928 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1624. Min Range: -8.1624
Max Act: 7.5999. Min Act: -0.1700
Data Index: 550139 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1624. Min Range: -8.1624
Max Act: 7.5999. Min Act: -0.1700
Data Index: 2937210 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1624. Min Range: -8.1624
Max Act: 7.5687. Min Act: -0.1700
Data Index: 4676091 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1624. Min Range: -8.1624
Max Act: 7.5062. Min Act: -0.1700
Data Index: 1634331 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19