Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3974 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2320. Min Range: -5.2320
Max Act: 5.2320. Min Act: -0.1700
Data Index: 1413371 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2320. Min Range: -5.2320
Max Act: 5.2008. Min Act: -0.1700
Data Index: 4705640 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2320. Min Range: -5.2320
Max Act: 5.2008. Min Act: -0.1700
Data Index: 8778902 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2320. Min Range: -5.2320
Max Act: 5.1695. Min Act: -0.1700
Data Index: 5497521 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2320. Min Range: -5.2320
Max Act: 5.1695. Min Act: -0.1700
Data Index: 2077771 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2320. Min Range: -5.2320
Max Act: 5.1695. Min Act: -0.1700
Data Index: 6419763 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2320. Min Range: -5.2320
Max Act: 5.1695. Min Act: -0.1700
Data Index: 8428112 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2320. Min Range: -5.2320
Max Act: 5.1695. Min Act: -0.1700
Data Index: 7673962 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2320. Min Range: -5.2320
Max Act: 5.1383. Min Act: -0.1700
Data Index: 248408 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2320. Min Range: -5.2320
Max Act: 5.1383. Min Act: -0.1700
Data Index: 2076088 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2320. Min Range: -5.2320
Max Act: 5.1070. Min Act: -0.1700
Data Index: 783518 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2320. Min Range: -5.2320
Max Act: 5.1383. Min Act: -0.1700
Data Index: 5493910 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2320. Min Range: -5.2320
Max Act: 5.1383. Min Act: -0.1700
Data Index: 4739668 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2320. Min Range: -5.2320
Max Act: 5.1383. Min Act: -0.1700
Data Index: 7353028 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2320. Min Range: -5.2320
Max Act: 5.1383. Min Act: -0.1700
Data Index: 1563439 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2320. Min Range: -5.2320
Max Act: 5.1070. Min Act: -0.1700
Data Index: 5866375 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2320. Min Range: -5.2320
Max Act: 5.1070. Min Act: -0.1700
Data Index: 5837485 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2320. Min Range: -5.2320
Max Act: 5.1070. Min Act: -0.1700
Data Index: 8570256 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2320. Min Range: -5.2320
Max Act: 5.1070. Min Act: -0.1700
Data Index: 6021450 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2320. Min Range: -5.2320
Max Act: 5.0758. Min Act: -0.1700
Data Index: 1211666 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19