Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 320 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4295. Min Range: -8.4295
Max Act: 8.4295. Min Act: -0.1700
Data Index: 7728257 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4295. Min Range: -8.4295
Max Act: 8.2420. Min Act: -0.1700
Data Index: 1696710 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4295. Min Range: -8.4295
Max Act: 8.0545. Min Act: -0.1700
Data Index: 3002015 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4295. Min Range: -8.4295
Max Act: 8.0545. Min Act: -0.1700
Data Index: 5434888 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4295. Min Range: -8.4295
Max Act: 7.8670. Min Act: -0.1700
Data Index: 7152398 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4295. Min Range: -8.4295
Max Act: 7.8357. Min Act: -0.1700
Data Index: 6739625 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4295. Min Range: -8.4295
Max Act: 7.8357. Min Act: -0.1700
Data Index: 54056 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4295. Min Range: -8.4295
Max Act: 7.8045. Min Act: -0.1700
Data Index: 6987691 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4295. Min Range: -8.4295
Max Act: 7.8357. Min Act: -0.1700
Data Index: 390608 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4295. Min Range: -8.4295
Max Act: 7.7732. Min Act: -0.1700
Data Index: 1787046 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4295. Min Range: -8.4295
Max Act: 7.8045. Min Act: -0.1700
Data Index: 3006678 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4295. Min Range: -8.4295
Max Act: 7.7732. Min Act: -0.1700
Data Index: 7176625 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4295. Min Range: -8.4295
Max Act: 7.7732. Min Act: -0.1700
Data Index: 3697836 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4295. Min Range: -8.4295
Max Act: 7.7107. Min Act: -0.1700
Data Index: 688927 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4295. Min Range: -8.4295
Max Act: 7.7107. Min Act: -0.1700
Data Index: 5176332 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4295. Min Range: -8.4295
Max Act: 7.7107. Min Act: -0.1700
Data Index: 1509431 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4295. Min Range: -8.4295
Max Act: 7.6482. Min Act: -0.1700
Data Index: 1171388 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4295. Min Range: -8.4295
Max Act: 7.6170. Min Act: -0.1700
Data Index: 3778512 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4295. Min Range: -8.4295
Max Act: 7.6170. Min Act: -0.1700
Data Index: 5493760 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4295. Min Range: -8.4295
Max Act: 7.5857. Min Act: -0.1700
Data Index: 4562848 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19