Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5098 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2564. Min Range: -7.2564
Max Act: 7.2564. Min Act: -0.1700
Data Index: 5709751 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2564. Min Range: -7.2564
Max Act: 7.2564. Min Act: -0.1700
Data Index: 7229459 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2564. Min Range: -7.2564
Max Act: 7.2564. Min Act: -0.1700
Data Index: 4635909 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2564. Min Range: -7.2564
Max Act: 7.2252. Min Act: -0.1700
Data Index: 1076272 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2564. Min Range: -7.2564
Max Act: 7.1627. Min Act: -0.1700
Data Index: 4805206 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2564. Min Range: -7.2564
Max Act: 7.1939. Min Act: -0.1700
Data Index: 5957196 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2564. Min Range: -7.2564
Max Act: 7.0689. Min Act: -0.1700
Data Index: 3675576 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2564. Min Range: -7.2564
Max Act: 7.0689. Min Act: -0.1700
Data Index: 4800593 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2564. Min Range: -7.2564
Max Act: 7.0377. Min Act: -0.1700
Data Index: 8405208 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2564. Min Range: -7.2564
Max Act: 7.0377. Min Act: -0.1700
Data Index: 993734 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2564. Min Range: -7.2564
Max Act: 7.0064. Min Act: -0.1700
Data Index: 8533103 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2564. Min Range: -7.2564
Max Act: 6.9439. Min Act: -0.1700
Data Index: 7659972 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2564. Min Range: -7.2564
Max Act: 6.9752. Min Act: -0.1700
Data Index: 3886974 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2564. Min Range: -7.2564
Max Act: 6.9127. Min Act: -0.1700
Data Index: 2656981 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2564. Min Range: -7.2564
Max Act: 6.8814. Min Act: -0.1700
Data Index: 7131466 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2564. Min Range: -7.2564
Max Act: 6.8814. Min Act: -0.1700
Data Index: 6262731 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2564. Min Range: -7.2564
Max Act: 6.8502. Min Act: -0.1700
Data Index: 4542667 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2564. Min Range: -7.2564
Max Act: 6.8189. Min Act: -0.1700
Data Index: 1980856 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2564. Min Range: -7.2564
Max Act: 6.8189. Min Act: -0.1700
Data Index: 1059797 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2564. Min Range: -7.2564
Max Act: 6.8189. Min Act: -0.1700
Data Index: 7737305 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19