Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6393 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3963. Min Range: -5.3963
Max Act: 5.3963. Min Act: -0.1700
Data Index: 5311614 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3963. Min Range: -5.3963
Max Act: 5.3338. Min Act: -0.1700
Data Index: 807919 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3963. Min Range: -5.3963
Max Act: 5.3338. Min Act: -0.1700
Data Index: 8440253 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3963. Min Range: -5.3963
Max Act: 5.3026. Min Act: -0.1700
Data Index: 1210554 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3963. Min Range: -5.3963
Max Act: 5.3338. Min Act: -0.1700
Data Index: 328486 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3963. Min Range: -5.3963
Max Act: 5.3026. Min Act: -0.1700
Data Index: 2188714 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3963. Min Range: -5.3963
Max Act: 5.2713. Min Act: -0.1700
Data Index: 3755952 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3963. Min Range: -5.3963
Max Act: 5.2401. Min Act: -0.1700
Data Index: 1405505 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3963. Min Range: -5.3963
Max Act: 5.2401. Min Act: -0.1700
Data Index: 2907645 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3963. Min Range: -5.3963
Max Act: 5.2401. Min Act: -0.1700
Data Index: 5016005 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3963. Min Range: -5.3963
Max Act: 5.2088. Min Act: -0.1700
Data Index: 8225502 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3963. Min Range: -5.3963
Max Act: 5.2088. Min Act: -0.1700
Data Index: 6920515 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3963. Min Range: -5.3963
Max Act: 5.1776. Min Act: -0.1700
Data Index: 3023645 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3963. Min Range: -5.3963
Max Act: 5.1776. Min Act: -0.1700
Data Index: 2202024 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3963. Min Range: -5.3963
Max Act: 5.1776. Min Act: -0.1700
Data Index: 1595824 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3963. Min Range: -5.3963
Max Act: 5.2088. Min Act: -0.1700
Data Index: 7425358 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3963. Min Range: -5.3963
Max Act: 5.1776. Min Act: -0.1700
Data Index: 6169299 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3963. Min Range: -5.3963
Max Act: 5.1463. Min Act: -0.1700
Data Index: 406979 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3963. Min Range: -5.3963
Max Act: 5.1463. Min Act: -0.1700
Data Index: 3869113 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3963. Min Range: -5.3963
Max Act: 5.1463. Min Act: -0.1700
Data Index: 5553933 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19