Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3807 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4098. Min Range: -7.4098
Max Act: 7.4098. Min Act: -0.1700
Data Index: 6443920 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4098. Min Range: -7.4098
Max Act: 7.1910. Min Act: -0.1699
Data Index: 6067339 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4098. Min Range: -7.4098
Max Act: 7.1910. Min Act: -0.1700
Data Index: 1384000 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4098. Min Range: -7.4098
Max Act: 7.1285. Min Act: -0.1700
Data Index: 8569035 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4098. Min Range: -7.4098
Max Act: 7.1285. Min Act: -0.1700
Data Index: 4322334 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4098. Min Range: -7.4098
Max Act: 7.0973. Min Act: -0.1700
Data Index: 420417 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4098. Min Range: -7.4098
Max Act: 7.0660. Min Act: -0.1700
Data Index: 6512424 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4098. Min Range: -7.4098
Max Act: 7.0660. Min Act: -0.1700
Data Index: 5730053 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4098. Min Range: -7.4098
Max Act: 7.0035. Min Act: -0.1700
Data Index: 3098143 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4098. Min Range: -7.4098
Max Act: 7.0035. Min Act: -0.1700
Data Index: 7264632 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4098. Min Range: -7.4098
Max Act: 7.0035. Min Act: -0.1700
Data Index: 5866619 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4098. Min Range: -7.4098
Max Act: 6.9723. Min Act: -0.1700
Data Index: 3765395 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4098. Min Range: -7.4098
Max Act: 6.9723. Min Act: -0.1700
Data Index: 1244626 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4098. Min Range: -7.4098
Max Act: 6.9723. Min Act: -0.1700
Data Index: 4863763 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4098. Min Range: -7.4098
Max Act: 6.9410. Min Act: -0.1700
Data Index: 1811545 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4098. Min Range: -7.4098
Max Act: 6.9723. Min Act: -0.1700
Data Index: 8267296 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4098. Min Range: -7.4098
Max Act: 6.9410. Min Act: -0.1700
Data Index: 2271091 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4098. Min Range: -7.4098
Max Act: 6.8785. Min Act: -0.1700
Data Index: 782207 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4098. Min Range: -7.4098
Max Act: 6.9723. Min Act: -0.1700
Data Index: 6189657 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4098. Min Range: -7.4098
Max Act: 6.9723. Min Act: -0.1700
Data Index: 7361301 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19