Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2505 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7242. Min Range: -3.7242
Max Act: 3.7242. Min Act: -0.1700
Data Index: 1330175 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7242. Min Range: -3.7242
Max Act: 3.6929. Min Act: -0.1700
Data Index: 4493782 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7242. Min Range: -3.7242
Max Act: 3.6460. Min Act: -0.1700
Data Index: 3952179 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7242. Min Range: -3.7242
Max Act: 3.5834. Min Act: -0.1700
Data Index: 8209706 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7242. Min Range: -3.7242
Max Act: 3.5364. Min Act: -0.1700
Data Index: 4618810 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7242. Min Range: -3.7242
Max Act: 3.5364. Min Act: -0.1700
Data Index: 1482862 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7242. Min Range: -3.7242
Max Act: 3.4894. Min Act: -0.1700
Data Index: 8581530 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7242. Min Range: -3.7242
Max Act: 3.4894. Min Act: -0.1700
Data Index: 1589771 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7242. Min Range: -3.7242
Max Act: 3.5051. Min Act: -0.1700
Data Index: 2236378 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7242. Min Range: -3.7242
Max Act: 3.4894. Min Act: -0.1700
Data Index: 6809124 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7242. Min Range: -3.7242
Max Act: 3.4738. Min Act: -0.1700
Data Index: 3409806 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7242. Min Range: -3.7242
Max Act: 3.4424. Min Act: -0.1700
Data Index: 5180568 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7242. Min Range: -3.7242
Max Act: 3.4424. Min Act: -0.1700
Data Index: 358612 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7242. Min Range: -3.7242
Max Act: 3.4424. Min Act: -0.1700
Data Index: 6230660 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7242. Min Range: -3.7242
Max Act: 3.3954. Min Act: -0.1700
Data Index: 4850059 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7242. Min Range: -3.7242
Max Act: 3.4424. Min Act: -0.1700
Data Index: 6282796 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7242. Min Range: -3.7242
Max Act: 3.3954. Min Act: -0.1700
Data Index: 8187817 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7242. Min Range: -3.7242
Max Act: 3.3797. Min Act: -0.1700
Data Index: 8392049 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7242. Min Range: -3.7242
Max Act: 3.3954. Min Act: -0.1700
Data Index: 8056237 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7242. Min Range: -3.7242
Max Act: 3.3954. Min Act: -0.1700
Data Index: 5701218 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19