Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 748 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9699. Min Range: -5.9699
Max Act: 5.9699. Min Act: -0.1700
Data Index: 2417482 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9699. Min Range: -5.9699
Max Act: 5.9386. Min Act: -0.1700
Data Index: 1102647 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9699. Min Range: -5.9699
Max Act: 5.9074. Min Act: -0.1700
Data Index: 3344830 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9699. Min Range: -5.9699
Max Act: 5.8449. Min Act: -0.1700
Data Index: 5289175 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9699. Min Range: -5.9699
Max Act: 5.8449. Min Act: -0.1700
Data Index: 5396569 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9699. Min Range: -5.9699
Max Act: 5.8136. Min Act: -0.1700
Data Index: 4715835 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9699. Min Range: -5.9699
Max Act: 5.7824. Min Act: -0.1700
Data Index: 6153144 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9699. Min Range: -5.9699
Max Act: 5.7199. Min Act: -0.1700
Data Index: 4581664 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9699. Min Range: -5.9699
Max Act: 5.6886. Min Act: -0.1700
Data Index: 2698651 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9699. Min Range: -5.9699
Max Act: 5.6261. Min Act: -0.1700
Data Index: 5643748 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9699. Min Range: -5.9699
Max Act: 5.6261. Min Act: -0.1700
Data Index: 3153928 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9699. Min Range: -5.9699
Max Act: 5.6261. Min Act: -0.1700
Data Index: 4972014 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9699. Min Range: -5.9699
Max Act: 5.6261. Min Act: -0.1700
Data Index: 1181839 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9699. Min Range: -5.9699
Max Act: 5.5636. Min Act: -0.1700
Data Index: 666289 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9699. Min Range: -5.9699
Max Act: 5.5949. Min Act: -0.1700
Data Index: 3177519 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9699. Min Range: -5.9699
Max Act: 5.5949. Min Act: -0.1700
Data Index: 227280 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9699. Min Range: -5.9699
Max Act: 5.5949. Min Act: -0.1700
Data Index: 6961721 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9699. Min Range: -5.9699
Max Act: 5.5949. Min Act: -0.1700
Data Index: 5172130 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9699. Min Range: -5.9699
Max Act: 5.5949. Min Act: -0.1700
Data Index: 3634966 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9699. Min Range: -5.9699
Max Act: 5.5636. Min Act: -0.1700
Data Index: 322882 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19