Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1293 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.8670. Min Act: -0.1700
Data Index: 8281768 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.8045. Min Act: -0.1700
Data Index: 3164570 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.8045. Min Act: -0.1700
Data Index: 18791 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.8045. Min Act: -0.1700
Data Index: 3382795 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.8045. Min Act: -0.1700
Data Index: 753006 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.8045. Min Act: -0.1700
Data Index: 4043174 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.7732. Min Act: -0.1700
Data Index: 5016030 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.7420. Min Act: -0.1700
Data Index: 2787872 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.7107. Min Act: -0.1700
Data Index: 7584097 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.6795. Min Act: -0.1700
Data Index: 4096489 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.7107. Min Act: -0.1700
Data Index: 441065 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.7107. Min Act: -0.1700
Data Index: 6926802 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.7107. Min Act: -0.1700
Data Index: 2458361 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.6795. Min Act: -0.1700
Data Index: 589173 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.6482. Min Act: -0.1700
Data Index: 2488961 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.6795. Min Act: -0.1700
Data Index: 5408731 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.6795. Min Act: -0.1700
Data Index: 2857024 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.6482. Min Act: -0.1700
Data Index: 6656338 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.6482. Min Act: -0.1700
Data Index: 2296607 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.6482. Min Act: -0.1700
Data Index: 1048314 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19