Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6332 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2552. Min Range: -7.2552
Max Act: 7.2552. Min Act: -0.1700
Data Index: 7648318 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2552. Min Range: -7.2552
Max Act: 7.0052. Min Act: -0.1700
Data Index: 6762552 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2552. Min Range: -7.2552
Max Act: 6.9739. Min Act: -0.1700
Data Index: 5116810 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2552. Min Range: -7.2552
Max Act: 6.9739. Min Act: -0.1700
Data Index: 2755966 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2552. Min Range: -7.2552
Max Act: 6.9739. Min Act: -0.1700
Data Index: 298313 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2552. Min Range: -7.2552
Max Act: 6.9427. Min Act: -0.1700
Data Index: 5640741 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2552. Min Range: -7.2552
Max Act: 6.8489. Min Act: -0.1700
Data Index: 7745047 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2552. Min Range: -7.2552
Max Act: 6.7864. Min Act: -0.1700
Data Index: 7787416 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2552. Min Range: -7.2552
Max Act: 6.7552. Min Act: -0.1700
Data Index: 3354858 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2552. Min Range: -7.2552
Max Act: 6.7552. Min Act: -0.1700
Data Index: 1863477 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2552. Min Range: -7.2552
Max Act: 6.7239. Min Act: -0.1700
Data Index: 3883759 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2552. Min Range: -7.2552
Max Act: 6.7552. Min Act: -0.1700
Data Index: 8096395 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2552. Min Range: -7.2552
Max Act: 6.7239. Min Act: -0.1700
Data Index: 4556438 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2552. Min Range: -7.2552
Max Act: 6.6927. Min Act: -0.1700
Data Index: 8181251 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2552. Min Range: -7.2552
Max Act: 6.6614. Min Act: -0.1700
Data Index: 480771 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2552. Min Range: -7.2552
Max Act: 6.6302. Min Act: -0.1700
Data Index: 8747768 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2552. Min Range: -7.2552
Max Act: 6.6302. Min Act: -0.1700
Data Index: 6647641 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2552. Min Range: -7.2552
Max Act: 6.5989. Min Act: -0.1700
Data Index: 159242 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2552. Min Range: -7.2552
Max Act: 6.6302. Min Act: -0.1700
Data Index: 635996 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2552. Min Range: -7.2552
Max Act: 6.5989. Min Act: -0.1700
Data Index: 4608997 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19