Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3262 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.8988. Min Act: -0.1700
Data Index: 838699 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6800. Min Act: -0.1700
Data Index: 7086740 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6800. Min Act: -0.1700
Data Index: 7984390 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.4300. Min Act: -0.1700
Data Index: 8188009 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.4300. Min Act: -0.1700
Data Index: 7296280 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.3988. Min Act: -0.1700
Data Index: 2741984 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.3675. Min Act: -0.1700
Data Index: 6239081 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.3675. Min Act: -0.1700
Data Index: 1569711 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.3675. Min Act: -0.1700
Data Index: 6212815 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.3050. Min Act: -0.1700
Data Index: 1926605 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.1800. Min Act: -0.1700
Data Index: 8813745 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.1175. Min Act: -0.1700
Data Index: 650093 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.1175. Min Act: -0.1700
Data Index: 7328285 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.0863. Min Act: -0.1700
Data Index: 7170709 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.1175. Min Act: -0.1700
Data Index: 4777745 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.0238. Min Act: -0.1700
Data Index: 8753915 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8988. Min Range: -6.8988
Max Act: 5.9925. Min Act: -0.1700
Data Index: 7772937 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8988. Min Range: -6.8988
Max Act: 5.9925. Min Act: -0.1700
Data Index: 7723570 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.0238. Min Act: -0.1700
Data Index: 1114542 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.0238. Min Act: -0.1700
Data Index: 2819658 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19