Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1817 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3028. Min Range: -4.3028
Max Act: 4.3028. Min Act: -0.1700
Data Index: 8808811 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3028. Min Range: -4.3028
Max Act: 4.2716. Min Act: -0.1700
Data Index: 7790291 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3028. Min Range: -4.3028
Max Act: 4.1465. Min Act: -0.1700
Data Index: 5081745 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3028. Min Range: -4.3028
Max Act: 4.1153. Min Act: -0.1700
Data Index: 3675523 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3028. Min Range: -4.3028
Max Act: 4.1153. Min Act: -0.1700
Data Index: 2653064 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3028. Min Range: -4.3028
Max Act: 4.0840. Min Act: -0.1700
Data Index: 1139602 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3028. Min Range: -4.3028
Max Act: 4.0528. Min Act: -0.1700
Data Index: 4991911 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3028. Min Range: -4.3028
Max Act: 4.0528. Min Act: -0.1700
Data Index: 298381 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3028. Min Range: -4.3028
Max Act: 4.0528. Min Act: -0.1700
Data Index: 1163992 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3028. Min Range: -4.3028
Max Act: 4.0215. Min Act: -0.1700
Data Index: 2125697 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3028. Min Range: -4.3028
Max Act: 3.9903. Min Act: -0.1700
Data Index: 2807756 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3028. Min Range: -4.3028
Max Act: 3.9590. Min Act: -0.1700
Data Index: 6137284 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3028. Min Range: -4.3028
Max Act: 3.9277. Min Act: -0.1700
Data Index: 7717042 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3028. Min Range: -4.3028
Max Act: 3.9590. Min Act: -0.1700
Data Index: 6902615 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3028. Min Range: -4.3028
Max Act: 3.8965. Min Act: -0.1700
Data Index: 7878281 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3028. Min Range: -4.3028
Max Act: 3.8965. Min Act: -0.1700
Data Index: 7449705 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3028. Min Range: -4.3028
Max Act: 3.8965. Min Act: -0.1700
Data Index: 7998758 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3028. Min Range: -4.3028
Max Act: 3.8965. Min Act: -0.1700
Data Index: 2413226 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3028. Min Range: -4.3028
Max Act: 3.8652. Min Act: -0.1700
Data Index: 923024 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3028. Min Range: -4.3028
Max Act: 3.8652. Min Act: -0.1700
Data Index: 2737202 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19