Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4884 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3841. Min Range: -7.3841
Max Act: 7.3841. Min Act: -0.1700
Data Index: 1891866 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3841. Min Range: -7.3841
Max Act: 7.1654. Min Act: -0.1700
Data Index: 6318402 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3841. Min Range: -7.3841
Max Act: 7.1341. Min Act: -0.1700
Data Index: 3602739 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3841. Min Range: -7.3841
Max Act: 7.0716. Min Act: -0.1700
Data Index: 3308392 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3841. Min Range: -7.3841
Max Act: 6.9779. Min Act: -0.1700
Data Index: 6261832 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3841. Min Range: -7.3841
Max Act: 6.9466. Min Act: -0.1700
Data Index: 4695397 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3841. Min Range: -7.3841
Max Act: 6.9154. Min Act: -0.1700
Data Index: 4467540 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3841. Min Range: -7.3841
Max Act: 6.9154. Min Act: -0.1700
Data Index: 8281047 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3841. Min Range: -7.3841
Max Act: 6.8841. Min Act: -0.1700
Data Index: 1498022 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3841. Min Range: -7.3841
Max Act: 6.8841. Min Act: -0.1700
Data Index: 4727321 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3841. Min Range: -7.3841
Max Act: 6.8529. Min Act: -0.1700
Data Index: 498083 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3841. Min Range: -7.3841
Max Act: 6.8529. Min Act: -0.1700
Data Index: 5065070 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3841. Min Range: -7.3841
Max Act: 6.8216. Min Act: -0.1700
Data Index: 4680574 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3841. Min Range: -7.3841
Max Act: 6.8216. Min Act: -0.1700
Data Index: 8800705 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3841. Min Range: -7.3841
Max Act: 6.8216. Min Act: -0.1700
Data Index: 5646022 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3841. Min Range: -7.3841
Max Act: 6.7904. Min Act: -0.1700
Data Index: 8187100 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3841. Min Range: -7.3841
Max Act: 6.7904. Min Act: -0.1700
Data Index: 2325252 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3841. Min Range: -7.3841
Max Act: 6.7904. Min Act: -0.1700
Data Index: 4030159 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3841. Min Range: -7.3841
Max Act: 6.7591. Min Act: -0.1700
Data Index: 199105 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3841. Min Range: -7.3841
Max Act: 6.7591. Min Act: -0.1700
Data Index: 7931244 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19