Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 121 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0555. Min Range: -6.0555
Max Act: 6.0555. Min Act: -0.1700
Data Index: 1105250 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0555. Min Range: -6.0555
Max Act: 5.9305. Min Act: -0.1700
Data Index: 3854930 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0555. Min Range: -6.0555
Max Act: 5.7118. Min Act: -0.1700
Data Index: 2381653 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0555. Min Range: -6.0555
Max Act: 5.6493. Min Act: -0.1700
Data Index: 5023768 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0555. Min Range: -6.0555
Max Act: 5.6493. Min Act: -0.1700
Data Index: 6154880 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0555. Min Range: -6.0555
Max Act: 5.6493. Min Act: -0.1700
Data Index: 6307936 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0555. Min Range: -6.0555
Max Act: 5.6180. Min Act: -0.1700
Data Index: 4073319 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0555. Min Range: -6.0555
Max Act: 5.5868. Min Act: -0.1700
Data Index: 489802 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0555. Min Range: -6.0555
Max Act: 5.5868. Min Act: -0.1700
Data Index: 8371409 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0555. Min Range: -6.0555
Max Act: 5.5868. Min Act: -0.1700
Data Index: 6669346 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0555. Min Range: -6.0555
Max Act: 5.5868. Min Act: -0.1700
Data Index: 657663 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0555. Min Range: -6.0555
Max Act: 5.5868. Min Act: -0.1700
Data Index: 449463 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0555. Min Range: -6.0555
Max Act: 5.5555. Min Act: -0.1700
Data Index: 6986094 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0555. Min Range: -6.0555
Max Act: 5.5555. Min Act: -0.1700
Data Index: 2682029 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0555. Min Range: -6.0555
Max Act: 5.5243. Min Act: -0.1700
Data Index: 2473516 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0555. Min Range: -6.0555
Max Act: 5.5555. Min Act: -0.1700
Data Index: 833752 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0555. Min Range: -6.0555
Max Act: 5.5243. Min Act: -0.1700
Data Index: 3356940 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0555. Min Range: -6.0555
Max Act: 5.5243. Min Act: -0.1700
Data Index: 639948 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0555. Min Range: -6.0555
Max Act: 5.5243. Min Act: -0.1700
Data Index: 1443266 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0555. Min Range: -6.0555
Max Act: 5.5243. Min Act: -0.1700
Data Index: 4215541 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19