Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3037 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6799. Min Range: -6.6799
Max Act: 6.6799. Min Act: -0.1700
Data Index: 4606569 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6799. Min Range: -6.6799
Max Act: 6.6487. Min Act: -0.1700
Data Index: 5316298 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6799. Min Range: -6.6799
Max Act: 6.5549. Min Act: -0.1700
Data Index: 2508987 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6799. Min Range: -6.6799
Max Act: 6.5237. Min Act: -0.1700
Data Index: 8658586 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6799. Min Range: -6.6799
Max Act: 6.5237. Min Act: -0.1700
Data Index: 8324027 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6799. Min Range: -6.6799
Max Act: 6.4924. Min Act: -0.1700
Data Index: 4648328 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6799. Min Range: -6.6799
Max Act: 6.4612. Min Act: -0.1700
Data Index: 2896299 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6799. Min Range: -6.6799
Max Act: 6.4612. Min Act: -0.1700
Data Index: 7081877 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6799. Min Range: -6.6799
Max Act: 6.4612. Min Act: -0.1700
Data Index: 6711596 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6799. Min Range: -6.6799
Max Act: 6.4612. Min Act: -0.1700
Data Index: 4025806 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6799. Min Range: -6.6799
Max Act: 6.4612. Min Act: -0.1700
Data Index: 7668063 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6799. Min Range: -6.6799
Max Act: 6.4612. Min Act: -0.1700
Data Index: 6149904 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6799. Min Range: -6.6799
Max Act: 6.4299. Min Act: -0.1700
Data Index: 7139626 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6799. Min Range: -6.6799
Max Act: 6.4299. Min Act: -0.1700
Data Index: 2017717 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6799. Min Range: -6.6799
Max Act: 6.3987. Min Act: -0.1700
Data Index: 4552492 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6799. Min Range: -6.6799
Max Act: 6.4299. Min Act: -0.1700
Data Index: 5772099 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6799. Min Range: -6.6799
Max Act: 6.3987. Min Act: -0.1700
Data Index: 8733253 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6799. Min Range: -6.6799
Max Act: 6.4612. Min Act: -0.1700
Data Index: 3717075 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6799. Min Range: -6.6799
Max Act: 6.4299. Min Act: -0.1700
Data Index: 4386931 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6799. Min Range: -6.6799
Max Act: 6.3987. Min Act: -0.1700
Data Index: 1491922 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19