Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1851 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0542. Min Range: -3.0542
Max Act: 3.0542. Min Act: -0.1700
Data Index: 1768520 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0542. Min Range: -3.0542
Max Act: 3.0542. Min Act: -0.1700
Data Index: 4269795 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0542. Min Range: -3.0542
Max Act: 3.0542. Min Act: -0.1700
Data Index: 611356 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0542. Min Range: -3.0542
Max Act: 3.0068. Min Act: -0.1700
Data Index: 6665823 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0542. Min Range: -3.0542
Max Act: 2.9277. Min Act: -0.1700
Data Index: 815140 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0542. Min Range: -3.0542
Max Act: 2.9119. Min Act: -0.1700
Data Index: 5796390 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0542. Min Range: -3.0542
Max Act: 2.9277. Min Act: -0.1700
Data Index: 569009 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0542. Min Range: -3.0542
Max Act: 2.9277. Min Act: -0.1700
Data Index: 6731221 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0542. Min Range: -3.0542
Max Act: 2.9119. Min Act: -0.1700
Data Index: 4796401 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0542. Min Range: -3.0542
Max Act: 2.9119. Min Act: -0.1700
Data Index: 2161367 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0542. Min Range: -3.0542
Max Act: 2.9119. Min Act: -0.1700
Data Index: 7410456 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0542. Min Range: -3.0542
Max Act: 2.9119. Min Act: -0.1700
Data Index: 2628084 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0542. Min Range: -3.0542
Max Act: 2.9119. Min Act: -0.1700
Data Index: 5433901 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0542. Min Range: -3.0542
Max Act: 2.8960. Min Act: -0.1700
Data Index: 519202 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0542. Min Range: -3.0542
Max Act: 2.8960. Min Act: -0.1700
Data Index: 5085323 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0542. Min Range: -3.0542
Max Act: 2.8960. Min Act: -0.1700
Data Index: 7307922 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0542. Min Range: -3.0542
Max Act: 2.8960. Min Act: -0.1700
Data Index: 7267263 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0542. Min Range: -3.0542
Max Act: 2.8960. Min Act: -0.1700
Data Index: 7270317 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0542. Min Range: -3.0542
Max Act: 2.8801. Min Act: -0.1700
Data Index: 4769451 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0542. Min Range: -3.0542
Max Act: 2.8960. Min Act: -0.1700
Data Index: 7842780 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19