Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 938 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8626. Min Range: -3.8626
Max Act: 3.8626. Min Act: -0.1700
Data Index: 5339843 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8626. Min Range: -3.8626
Max Act: 3.8626. Min Act: -0.1700
Data Index: 7193590 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8626. Min Range: -3.8626
Max Act: 3.5497. Min Act: -0.1700
Data Index: 6660546 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8626. Min Range: -3.8626
Max Act: 3.5184. Min Act: -0.1700
Data Index: 6959870 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8626. Min Range: -3.8626
Max Act: 3.5184. Min Act: -0.1700
Data Index: 953412 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8626. Min Range: -3.8626
Max Act: 3.5340. Min Act: -0.1700
Data Index: 8153962 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8626. Min Range: -3.8626
Max Act: 3.4870. Min Act: -0.1700
Data Index: 3500366 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8626. Min Range: -3.8626
Max Act: 3.4870. Min Act: -0.1700
Data Index: 4614157 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8626. Min Range: -3.8626
Max Act: 3.4870. Min Act: -0.1700
Data Index: 7162568 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8626. Min Range: -3.8626
Max Act: 3.4714. Min Act: -0.1700
Data Index: 2114807 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8626. Min Range: -3.8626
Max Act: 3.4714. Min Act: -0.1700
Data Index: 9949 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8626. Min Range: -3.8626
Max Act: 3.4714. Min Act: -0.1700
Data Index: 8153960 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8626. Min Range: -3.8626
Max Act: 3.4400. Min Act: -0.1700
Data Index: 5544573 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8626. Min Range: -3.8626
Max Act: 3.4400. Min Act: -0.1700
Data Index: 6395199 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8626. Min Range: -3.8626
Max Act: 3.4557. Min Act: -0.1700
Data Index: 3973106 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8626. Min Range: -3.8626
Max Act: 3.4244. Min Act: -0.1700
Data Index: 8473525 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8626. Min Range: -3.8626
Max Act: 3.4244. Min Act: -0.1700
Data Index: 3579522 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8626. Min Range: -3.8626
Max Act: 3.4087. Min Act: -0.1700
Data Index: 1785309 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8626. Min Range: -3.8626
Max Act: 3.4087. Min Act: -0.1700
Data Index: 6124328 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8626. Min Range: -3.8626
Max Act: 3.4087. Min Act: -0.1700
Data Index: 3791923 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19