Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3645 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3746. Min Range: -7.3746
Max Act: 7.3746. Min Act: -0.1700
Data Index: 8031720 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3746. Min Range: -7.3746
Max Act: 7.3433. Min Act: -0.1700
Data Index: 8426972 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3746. Min Range: -7.3746
Max Act: 7.3121. Min Act: -0.1700
Data Index: 3250419 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3746. Min Range: -7.3746
Max Act: 7.2496. Min Act: -0.1700
Data Index: 5873460 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3746. Min Range: -7.3746
Max Act: 7.2496. Min Act: -0.1700
Data Index: 1028855 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3746. Min Range: -7.3746
Max Act: 7.2496. Min Act: -0.1700
Data Index: 6517899 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3746. Min Range: -7.3746
Max Act: 7.2496. Min Act: -0.1700
Data Index: 1643503 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3746. Min Range: -7.3746
Max Act: 7.1246. Min Act: -0.1700
Data Index: 2134888 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3746. Min Range: -7.3746
Max Act: 7.0621. Min Act: -0.1700
Data Index: 517915 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3746. Min Range: -7.3746
Max Act: 7.0621. Min Act: -0.1700
Data Index: 473932 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3746. Min Range: -7.3746
Max Act: 7.0308. Min Act: -0.1700
Data Index: 7844669 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3746. Min Range: -7.3746
Max Act: 6.9683. Min Act: -0.1700
Data Index: 6830300 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3746. Min Range: -7.3746
Max Act: 6.9683. Min Act: -0.1700
Data Index: 3717518 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3746. Min Range: -7.3746
Max Act: 6.9683. Min Act: -0.1700
Data Index: 3881567 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3746. Min Range: -7.3746
Max Act: 6.9683. Min Act: -0.1700
Data Index: 1721538 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3746. Min Range: -7.3746
Max Act: 6.9683. Min Act: -0.1700
Data Index: 7031108 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3746. Min Range: -7.3746
Max Act: 6.9371. Min Act: -0.1700
Data Index: 5557385 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3746. Min Range: -7.3746
Max Act: 6.9683. Min Act: -0.1700
Data Index: 4059732 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3746. Min Range: -7.3746
Max Act: 6.9683. Min Act: -0.1700
Data Index: 1428720 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3746. Min Range: -7.3746
Max Act: 6.9371. Min Act: -0.1700
Data Index: 5127691 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19