Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4090 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5088. Min Range: -6.5088
Max Act: 6.5088. Min Act: -0.1700
Data Index: 5652996 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5088. Min Range: -6.5088
Max Act: 6.4151. Min Act: -0.1700
Data Index: 3689310 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5088. Min Range: -6.5088
Max Act: 6.4463. Min Act: -0.1700
Data Index: 7118363 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5088. Min Range: -6.5088
Max Act: 6.4151. Min Act: -0.1700
Data Index: 7913853 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5088. Min Range: -6.5088
Max Act: 6.3526. Min Act: -0.1700
Data Index: 6692100 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5088. Min Range: -6.5088
Max Act: 6.2588. Min Act: -0.1700
Data Index: 792685 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5088. Min Range: -6.5088
Max Act: 6.1963. Min Act: -0.1700
Data Index: 7246688 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5088. Min Range: -6.5088
Max Act: 6.2276. Min Act: -0.1700
Data Index: 5010524 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5088. Min Range: -6.5088
Max Act: 6.1963. Min Act: -0.1700
Data Index: 2819370 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5088. Min Range: -6.5088
Max Act: 6.1338. Min Act: -0.1700
Data Index: 5576406 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5088. Min Range: -6.5088
Max Act: 6.1026. Min Act: -0.1700
Data Index: 5515764 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5088. Min Range: -6.5088
Max Act: 6.1651. Min Act: -0.1700
Data Index: 4144202 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5088. Min Range: -6.5088
Max Act: 6.1338. Min Act: -0.1700
Data Index: 8445656 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5088. Min Range: -6.5088
Max Act: 6.1026. Min Act: -0.1700
Data Index: 3777550 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5088. Min Range: -6.5088
Max Act: 6.0713. Min Act: -0.1700
Data Index: 6499530 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5088. Min Range: -6.5088
Max Act: 6.1338. Min Act: -0.1700
Data Index: 2675671 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5088. Min Range: -6.5088
Max Act: 6.0713. Min Act: -0.1700
Data Index: 6521714 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5088. Min Range: -6.5088
Max Act: 6.0713. Min Act: -0.1700
Data Index: 2849867 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5088. Min Range: -6.5088
Max Act: 6.0713. Min Act: -0.1700
Data Index: 3468309 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5088. Min Range: -6.5088
Max Act: 6.0401. Min Act: -0.1700
Data Index: 27173 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19