Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1848 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7522. Min Range: -4.7522
Max Act: 4.7522. Min Act: -0.1700
Data Index: 3703792 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7522. Min Range: -4.7522
Max Act: 4.7522. Min Act: -0.1700
Data Index: 7045226 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7522. Min Range: -4.7522
Max Act: 4.7209. Min Act: -0.1700
Data Index: 7958676 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7522. Min Range: -4.7522
Max Act: 4.6897. Min Act: -0.1700
Data Index: 4973760 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7522. Min Range: -4.7522
Max Act: 4.6584. Min Act: -0.1700
Data Index: 4758928 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7522. Min Range: -4.7522
Max Act: 4.6272. Min Act: -0.1700
Data Index: 5905923 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7522. Min Range: -4.7522
Max Act: 4.6272. Min Act: -0.1700
Data Index: 4543994 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7522. Min Range: -4.7522
Max Act: 4.6272. Min Act: -0.1700
Data Index: 1425494 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7522. Min Range: -4.7522
Max Act: 4.5959. Min Act: -0.1700
Data Index: 6883712 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7522. Min Range: -4.7522
Max Act: 4.5959. Min Act: -0.1700
Data Index: 349781 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7522. Min Range: -4.7522
Max Act: 4.5647. Min Act: -0.1700
Data Index: 3158072 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7522. Min Range: -4.7522
Max Act: 4.5022. Min Act: -0.1700
Data Index: 6764829 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7522. Min Range: -4.7522
Max Act: 4.5334. Min Act: -0.1700
Data Index: 7201887 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7522. Min Range: -4.7522
Max Act: 4.4709. Min Act: -0.1700
Data Index: 711019 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7522. Min Range: -4.7522
Max Act: 4.4709. Min Act: -0.1700
Data Index: 7004023 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7522. Min Range: -4.7522
Max Act: 4.4709. Min Act: -0.1700
Data Index: 5609278 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7522. Min Range: -4.7522
Max Act: 4.4397. Min Act: -0.1700
Data Index: 8122275 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7522. Min Range: -4.7522
Max Act: 4.4709. Min Act: -0.1700
Data Index: 7403182 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7522. Min Range: -4.7522
Max Act: 4.4397. Min Act: -0.1700
Data Index: 5786128 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7522. Min Range: -4.7522
Max Act: 4.4397. Min Act: -0.1700
Data Index: 530557 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19