Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3422 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0903. Min Range: -5.0903
Max Act: 5.0903. Min Act: -0.1700
Data Index: 7413883 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.9340. Min Act: -0.1700
Data Index: 1374681 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.9340. Min Act: -0.1700
Data Index: 1397026 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.9028. Min Act: -0.1700
Data Index: 8508550 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.8715. Min Act: -0.1700
Data Index: 3019761 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.8403. Min Act: -0.1700
Data Index: 5692196 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.8403. Min Act: -0.1700
Data Index: 8199208 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.8090. Min Act: -0.1700
Data Index: 2461906 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.7465. Min Act: -0.1700
Data Index: 1678336 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.7778. Min Act: -0.1700
Data Index: 3570208 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.7153. Min Act: -0.1700
Data Index: 7956721 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.7153. Min Act: -0.1700
Data Index: 7330962 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.7465. Min Act: -0.1700
Data Index: 3074336 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.7153. Min Act: -0.1700
Data Index: 6850587 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.6840. Min Act: -0.1700
Data Index: 2883850 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.6840. Min Act: -0.1700
Data Index: 760092 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.7153. Min Act: -0.1700
Data Index: 8139176 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.6528. Min Act: -0.1700
Data Index: 493910 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.6528. Min Act: -0.1700
Data Index: 3813614 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.6528. Min Act: -0.1700
Data Index: 6579779 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19