Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 485 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.5485. Min Act: -0.1700
Data Index: 4790520 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.5485. Min Act: -0.1700
Data Index: 8072689 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.4235. Min Act: -0.1700
Data Index: 6068969 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.2985. Min Act: -0.1700
Data Index: 7355771 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.2985. Min Act: -0.1700
Data Index: 3923260 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.2672. Min Act: -0.1700
Data Index: 1464273 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.2672. Min Act: -0.1700
Data Index: 8012946 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.2360. Min Act: -0.1700
Data Index: 4609893 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.2360. Min Act: -0.1700
Data Index: 3111649 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.2047. Min Act: -0.1700
Data Index: 8650411 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.1422. Min Act: -0.1700
Data Index: 5742619 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.1735. Min Act: -0.1700
Data Index: 1561493 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.1735. Min Act: -0.1700
Data Index: 3886121 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.1422. Min Act: -0.1700
Data Index: 4054952 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.1110. Min Act: -0.1700
Data Index: 4445570 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.1110. Min Act: -0.1700
Data Index: 1238893 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.1110. Min Act: -0.1700
Data Index: 7605068 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.0797. Min Act: -0.1700
Data Index: 696409 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.1110. Min Act: -0.1700
Data Index: 6899661 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.0797. Min Act: -0.1700
Data Index: 955422 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19