Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2875 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8525. Min Range: -7.8525
Max Act: 7.8525. Min Act: -0.1700
Data Index: 6764036 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8525. Min Range: -7.8525
Max Act: 7.6650. Min Act: -0.1700
Data Index: 7677842 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8525. Min Range: -7.8525
Max Act: 7.6337. Min Act: -0.1700
Data Index: 8482413 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8525. Min Range: -7.8525
Max Act: 7.6025. Min Act: -0.1700
Data Index: 941609 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8525. Min Range: -7.8525
Max Act: 7.5400. Min Act: -0.1700
Data Index: 5979566 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8525. Min Range: -7.8525
Max Act: 7.5400. Min Act: -0.1700
Data Index: 1882419 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8525. Min Range: -7.8525
Max Act: 7.4462. Min Act: -0.1700
Data Index: 8725788 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8525. Min Range: -7.8525
Max Act: 7.4150. Min Act: -0.1700
Data Index: 5044710 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8525. Min Range: -7.8525
Max Act: 7.3525. Min Act: -0.1700
Data Index: 3042438 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8525. Min Range: -7.8525
Max Act: 7.3525. Min Act: -0.1700
Data Index: 8335908 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8525. Min Range: -7.8525
Max Act: 7.3212. Min Act: -0.1700
Data Index: 1335999 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8525. Min Range: -7.8525
Max Act: 7.2900. Min Act: -0.1700
Data Index: 6546513 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8525. Min Range: -7.8525
Max Act: 7.2587. Min Act: -0.1700
Data Index: 5797844 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8525. Min Range: -7.8525
Max Act: 7.2587. Min Act: -0.1700
Data Index: 4236961 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8525. Min Range: -7.8525
Max Act: 7.2587. Min Act: -0.1700
Data Index: 941770 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8525. Min Range: -7.8525
Max Act: 7.2275. Min Act: -0.1700
Data Index: 2174509 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8525. Min Range: -7.8525
Max Act: 7.1962. Min Act: -0.1700
Data Index: 2748936 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8525. Min Range: -7.8525
Max Act: 7.1650. Min Act: -0.1700
Data Index: 7673110 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8525. Min Range: -7.8525
Max Act: 7.1650. Min Act: -0.1700
Data Index: 928585 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8525. Min Range: -7.8525
Max Act: 7.1650. Min Act: -0.1700
Data Index: 6357625 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19