Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4553 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8295. Min Range: -8.8295
Max Act: 8.8295. Min Act: -0.1700
Data Index: 529489 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8295. Min Range: -8.8295
Max Act: 8.5170. Min Act: -0.1700
Data Index: 7710613 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8295. Min Range: -8.8295
Max Act: 8.2670. Min Act: -0.1700
Data Index: 6119043 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8295. Min Range: -8.8295
Max Act: 8.2670. Min Act: -0.1700
Data Index: 1379821 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8295. Min Range: -8.8295
Max Act: 8.2670. Min Act: -0.1700
Data Index: 8467313 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8295. Min Range: -8.8295
Max Act: 8.2670. Min Act: -0.1700
Data Index: 2249065 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8295. Min Range: -8.8295
Max Act: 8.1732. Min Act: -0.1700
Data Index: 6712948 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8295. Min Range: -8.8295
Max Act: 8.2045. Min Act: -0.1700
Data Index: 8288218 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8295. Min Range: -8.8295
Max Act: 8.2045. Min Act: -0.1700
Data Index: 8028471 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8295. Min Range: -8.8295
Max Act: 8.1420. Min Act: -0.1700
Data Index: 3855824 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8295. Min Range: -8.8295
Max Act: 8.1420. Min Act: -0.1700
Data Index: 5275973 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8295. Min Range: -8.8295
Max Act: 8.1420. Min Act: -0.1700
Data Index: 1656708 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8295. Min Range: -8.8295
Max Act: 8.0795. Min Act: -0.1700
Data Index: 6715879 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8295. Min Range: -8.8295
Max Act: 8.0170. Min Act: -0.1700
Data Index: 4456153 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8295. Min Range: -8.8295
Max Act: 8.0482. Min Act: -0.1700
Data Index: 5254181 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8295. Min Range: -8.8295
Max Act: 8.0482. Min Act: -0.1700
Data Index: 8288211 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8295. Min Range: -8.8295
Max Act: 8.0170. Min Act: -0.1700
Data Index: 8439623 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8295. Min Range: -8.8295
Max Act: 8.0170. Min Act: -0.1700
Data Index: 510836 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8295. Min Range: -8.8295
Max Act: 8.0170. Min Act: -0.1700
Data Index: 2821622 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8295. Min Range: -8.8295
Max Act: 7.9857. Min Act: -0.1700
Data Index: 2850316 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19