Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 436 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.9827. Min Act: -0.1700
Data Index: 7525995 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.9827. Min Act: -0.1700
Data Index: 8371422 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.5764. Min Act: -0.1700
Data Index: 1526000 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.4827. Min Act: -0.1700
Data Index: 6448291 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.4514. Min Act: -0.1700
Data Index: 5619445 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.4202. Min Act: -0.1700
Data Index: 5619447 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.3889. Min Act: -0.1700
Data Index: 763713 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.3889. Min Act: -0.1700
Data Index: 6569721 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.3889. Min Act: -0.1700
Data Index: 6399552 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.3889. Min Act: -0.1700
Data Index: 584025 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.3577. Min Act: -0.1700
Data Index: 8077595 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.3577. Min Act: -0.1700
Data Index: 4782427 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.2952. Min Act: -0.1700
Data Index: 6176298 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.3264. Min Act: -0.1700
Data Index: 5553872 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.2952. Min Act: -0.1700
Data Index: 4604866 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.2952. Min Act: -0.1700
Data Index: 553617 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.3264. Min Act: -0.1700
Data Index: 4831731 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.2952. Min Act: -0.1700
Data Index: 96110 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.2327. Min Act: -0.1700
Data Index: 3397736 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.2639. Min Act: -0.1700
Data Index: 4916176 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19