Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5825 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0420. Min Range: -6.0420
Max Act: 6.0420. Min Act: -0.1700
Data Index: 5333836 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.8857. Min Act: -0.1700
Data Index: 2729806 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.8232. Min Act: -0.1700
Data Index: 1117881 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.8232. Min Act: -0.1700
Data Index: 6683235 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.7920. Min Act: -0.1700
Data Index: 5810788 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.7607. Min Act: -0.1700
Data Index: 6871957 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.6982. Min Act: -0.1700
Data Index: 1242808 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.6670. Min Act: -0.1700
Data Index: 4255947 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.6357. Min Act: -0.1700
Data Index: 2891770 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.6045. Min Act: -0.1700
Data Index: 5330402 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.5732. Min Act: -0.1700
Data Index: 1381579 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.6045. Min Act: -0.1700
Data Index: 8002837 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.5420. Min Act: -0.1700
Data Index: 8409850 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.5420. Min Act: -0.1700
Data Index: 3621521 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.5420. Min Act: -0.1700
Data Index: 4644397 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.5107. Min Act: -0.1700
Data Index: 2505929 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.4795. Min Act: -0.1700
Data Index: 996320 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.4795. Min Act: -0.1700
Data Index: 6760933 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.4795. Min Act: -0.1700
Data Index: 129531 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.4795. Min Act: -0.1700
Data Index: 296483 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19