Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5179 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1409. Min Range: -3.1409
Max Act: 3.1409. Min Act: -0.1700
Data Index: 155245 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1409. Min Range: -3.1409
Max Act: 3.1252. Min Act: -0.1700
Data Index: 2939540 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1409. Min Range: -3.1409
Max Act: 3.1252. Min Act: -0.1700
Data Index: 5276249 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1409. Min Range: -3.1409
Max Act: 3.0148. Min Act: -0.1700
Data Index: 3052530 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1409. Min Range: -3.1409
Max Act: 2.9990. Min Act: -0.1700
Data Index: 946012 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1409. Min Range: -3.1409
Max Act: 2.9515. Min Act: -0.1700
Data Index: 7291480 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1409. Min Range: -3.1409
Max Act: 2.9515. Min Act: -0.1700
Data Index: 4483134 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1409. Min Range: -3.1409
Max Act: 2.9198. Min Act: -0.1700
Data Index: 4599747 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1409. Min Range: -3.1409
Max Act: 2.9198. Min Act: -0.1700
Data Index: 8430524 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1409. Min Range: -3.1409
Max Act: 2.9198. Min Act: -0.1700
Data Index: 8316408 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1409. Min Range: -3.1409
Max Act: 2.9040. Min Act: -0.1700
Data Index: 4899434 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1409. Min Range: -3.1409
Max Act: 2.9040. Min Act: -0.1700
Data Index: 657293 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1409. Min Range: -3.1409
Max Act: 2.8881. Min Act: -0.1700
Data Index: 6097088 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1409. Min Range: -3.1409
Max Act: 2.8881. Min Act: -0.1700
Data Index: 4979477 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1409. Min Range: -3.1409
Max Act: 2.8723. Min Act: -0.1700
Data Index: 6477073 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1409. Min Range: -3.1409
Max Act: 2.8723. Min Act: -0.1700
Data Index: 6263431 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1409. Min Range: -3.1409
Max Act: 2.8881. Min Act: -0.1700
Data Index: 8361322 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1409. Min Range: -3.1409
Max Act: 2.8723. Min Act: -0.1700
Data Index: 8007475 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1409. Min Range: -3.1409
Max Act: 2.8405. Min Act: -0.1700
Data Index: 4269319 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1409. Min Range: -3.1409
Max Act: 2.8405. Min Act: -0.1700
Data Index: 769301 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19