Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4508 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7900. Min Range: -5.7900
Max Act: 5.7900. Min Act: -0.1700
Data Index: 5303195 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7900. Min Range: -5.7900
Max Act: 5.7275. Min Act: -0.1700
Data Index: 7812328 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7900. Min Range: -5.7900
Max Act: 5.6025. Min Act: -0.1700
Data Index: 7942355 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7900. Min Range: -5.7900
Max Act: 5.5712. Min Act: -0.1700
Data Index: 4483104 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7900. Min Range: -5.7900
Max Act: 5.5712. Min Act: -0.1700
Data Index: 4780270 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7900. Min Range: -5.7900
Max Act: 5.5087. Min Act: -0.1700
Data Index: 6726471 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7900. Min Range: -5.7900
Max Act: 5.5087. Min Act: -0.1700
Data Index: 7192898 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7900. Min Range: -5.7900
Max Act: 5.4775. Min Act: -0.1700
Data Index: 7772235 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7900. Min Range: -5.7900
Max Act: 5.4462. Min Act: -0.1700
Data Index: 5572382 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7900. Min Range: -5.7900
Max Act: 5.4150. Min Act: -0.1700
Data Index: 7697345 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7900. Min Range: -5.7900
Max Act: 5.4150. Min Act: -0.1700
Data Index: 7794352 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7900. Min Range: -5.7900
Max Act: 5.3837. Min Act: -0.1700
Data Index: 949463 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7900. Min Range: -5.7900
Max Act: 5.3837. Min Act: -0.1700
Data Index: 1351885 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7900. Min Range: -5.7900
Max Act: 5.3837. Min Act: -0.1700
Data Index: 4612959 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7900. Min Range: -5.7900
Max Act: 5.3525. Min Act: -0.1700
Data Index: 6948831 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7900. Min Range: -5.7900
Max Act: 5.3212. Min Act: -0.1700
Data Index: 7097689 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7900. Min Range: -5.7900
Max Act: 5.3525. Min Act: -0.1700
Data Index: 815007 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7900. Min Range: -5.7900
Max Act: 5.3525. Min Act: -0.1700
Data Index: 4562688 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7900. Min Range: -5.7900
Max Act: 5.3525. Min Act: -0.1700
Data Index: 3830878 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7900. Min Range: -5.7900
Max Act: 5.3525. Min Act: -0.1700
Data Index: 7495279 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19