Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4054 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1901. Min Range: -6.1901
Max Act: 6.1901. Min Act: -0.1700
Data Index: 4905880 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1901. Min Range: -6.1901
Max Act: 5.8463. Min Act: -0.1700
Data Index: 5155590 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1901. Min Range: -6.1901
Max Act: 5.6901. Min Act: -0.1700
Data Index: 5270532 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1901. Min Range: -6.1901
Max Act: 5.6901. Min Act: -0.1700
Data Index: 6861314 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1901. Min Range: -6.1901
Max Act: 5.5963. Min Act: -0.1700
Data Index: 8820758 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1901. Min Range: -6.1901
Max Act: 5.5338. Min Act: -0.1700
Data Index: 2316609 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1901. Min Range: -6.1901
Max Act: 5.5651. Min Act: -0.1700
Data Index: 7037039 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1901. Min Range: -6.1901
Max Act: 5.5651. Min Act: -0.1700
Data Index: 1288348 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1901. Min Range: -6.1901
Max Act: 5.5026. Min Act: -0.1700
Data Index: 43601 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1901. Min Range: -6.1901
Max Act: 5.4401. Min Act: -0.1700
Data Index: 5445808 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1901. Min Range: -6.1901
Max Act: 5.4401. Min Act: -0.1700
Data Index: 7318132 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1901. Min Range: -6.1901
Max Act: 5.3776. Min Act: -0.1700
Data Index: 4160434 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1901. Min Range: -6.1901
Max Act: 5.3463. Min Act: -0.1700
Data Index: 4312717 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1901. Min Range: -6.1901
Max Act: 5.3776. Min Act: -0.1700
Data Index: 6070317 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1901. Min Range: -6.1901
Max Act: 5.4088. Min Act: -0.1700
Data Index: 7695776 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1901. Min Range: -6.1901
Max Act: 5.3776. Min Act: -0.1700
Data Index: 7402014 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1901. Min Range: -6.1901
Max Act: 5.3776. Min Act: -0.1700
Data Index: 367325 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1901. Min Range: -6.1901
Max Act: 5.3463. Min Act: -0.1700
Data Index: 7466022 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1901. Min Range: -6.1901
Max Act: 5.3463. Min Act: -0.1700
Data Index: 4356625 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1901. Min Range: -6.1901
Max Act: 5.3463. Min Act: -0.1700
Data Index: 376558 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19