Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3554 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5742. Min Range: -7.5742
Max Act: 7.5742. Min Act: -0.1700
Data Index: 3064312 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5742. Min Range: -7.5742
Max Act: 7.4180. Min Act: -0.1700
Data Index: 2167439 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5742. Min Range: -7.5742
Max Act: 7.3242. Min Act: -0.1700
Data Index: 3304571 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5742. Min Range: -7.5742
Max Act: 7.0117. Min Act: -0.1700
Data Index: 4618044 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5742. Min Range: -7.5742
Max Act: 6.9805. Min Act: -0.1700
Data Index: 152721 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5742. Min Range: -7.5742
Max Act: 6.9805. Min Act: -0.1700
Data Index: 6572555 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5742. Min Range: -7.5742
Max Act: 6.9492. Min Act: -0.1700
Data Index: 5546998 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5742. Min Range: -7.5742
Max Act: 6.9180. Min Act: -0.1700
Data Index: 6430866 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5742. Min Range: -7.5742
Max Act: 6.8555. Min Act: -0.1700
Data Index: 6848233 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5742. Min Range: -7.5742
Max Act: 6.8555. Min Act: -0.1700
Data Index: 4197577 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5742. Min Range: -7.5742
Max Act: 6.8242. Min Act: -0.1700
Data Index: 448063 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5742. Min Range: -7.5742
Max Act: 6.7930. Min Act: -0.1700
Data Index: 3424769 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5742. Min Range: -7.5742
Max Act: 6.7617. Min Act: -0.1700
Data Index: 7938558 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5742. Min Range: -7.5742
Max Act: 6.7617. Min Act: -0.1700
Data Index: 4234746 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5742. Min Range: -7.5742
Max Act: 6.6992. Min Act: -0.1700
Data Index: 7650653 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5742. Min Range: -7.5742
Max Act: 6.6680. Min Act: -0.1700
Data Index: 8357587 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5742. Min Range: -7.5742
Max Act: 6.6367. Min Act: -0.1700
Data Index: 8489423 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5742. Min Range: -7.5742
Max Act: 6.6367. Min Act: -0.1700
Data Index: 5128536 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5742. Min Range: -7.5742
Max Act: 6.6367. Min Act: -0.1700
Data Index: 7136568 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5742. Min Range: -7.5742
Max Act: 6.6367. Min Act: -0.1700
Data Index: 2738564 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19