Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5782 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1499. Min Range: -7.1499
Max Act: 7.1499. Min Act: -0.1700
Data Index: 5976495 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1499. Min Range: -7.1499
Max Act: 7.0874. Min Act: -0.1700
Data Index: 2775087 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.9624. Min Act: -0.1700
Data Index: 2422991 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.7124. Min Act: -0.1700
Data Index: 5068920 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.7124. Min Act: -0.1700
Data Index: 3368043 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.6187. Min Act: -0.1700
Data Index: 2747748 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.6187. Min Act: -0.1700
Data Index: 8679914 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.6187. Min Act: -0.1700
Data Index: 5421140 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.6187. Min Act: -0.1700
Data Index: 7038481 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.5874. Min Act: -0.1700
Data Index: 8523937 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.5874. Min Act: -0.1700
Data Index: 7516563 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.5562. Min Act: -0.1700
Data Index: 6843341 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.5874. Min Act: -0.1700
Data Index: 5990643 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.5562. Min Act: -0.1700
Data Index: 6068733 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.4937. Min Act: -0.1700
Data Index: 7858998 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.4624. Min Act: -0.1700
Data Index: 7821211 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.4937. Min Act: -0.1700
Data Index: 124419 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.4937. Min Act: -0.1700
Data Index: 7451234 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.4624. Min Act: -0.1700
Data Index: 7300821 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.4624. Min Act: -0.1700
Data Index: 7609280 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19