Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3088 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3907. Min Range: -3.3907
Max Act: 3.3907. Min Act: -0.1700
Data Index: 859357 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3907. Min Range: -3.3907
Max Act: 3.3750. Min Act: -0.1700
Data Index: 2455807 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3907. Min Range: -3.3907
Max Act: 3.3280. Min Act: -0.1700
Data Index: 7607157 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3907. Min Range: -3.3907
Max Act: 3.2966. Min Act: -0.1700
Data Index: 628580 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3907. Min Range: -3.3907
Max Act: 3.2966. Min Act: -0.1700
Data Index: 7607155 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3907. Min Range: -3.3907
Max Act: 3.2809. Min Act: -0.1700
Data Index: 5352109 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3907. Min Range: -3.3907
Max Act: 3.2809. Min Act: -0.1700
Data Index: 4809766 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3907. Min Range: -3.3907
Max Act: 3.2809. Min Act: -0.1700
Data Index: 6514112 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3907. Min Range: -3.3907
Max Act: 3.2809. Min Act: -0.1700
Data Index: 2527100 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3907. Min Range: -3.3907
Max Act: 3.2809. Min Act: -0.1700
Data Index: 4259342 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3907. Min Range: -3.3907
Max Act: 3.2652. Min Act: -0.1700
Data Index: 5972375 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3907. Min Range: -3.3907
Max Act: 3.2652. Min Act: -0.1700
Data Index: 422060 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3907. Min Range: -3.3907
Max Act: 3.2652. Min Act: -0.1700
Data Index: 5352111 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3907. Min Range: -3.3907
Max Act: 3.2652. Min Act: -0.1700
Data Index: 4155775 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3907. Min Range: -3.3907
Max Act: 3.2495. Min Act: -0.1700
Data Index: 5920700 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3907. Min Range: -3.3907
Max Act: 3.2495. Min Act: -0.1700
Data Index: 5352105 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3907. Min Range: -3.3907
Max Act: 3.2495. Min Act: -0.1700
Data Index: 310475 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3907. Min Range: -3.3907
Max Act: 3.2495. Min Act: -0.1700
Data Index: 1700313 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3907. Min Range: -3.3907
Max Act: 3.2338. Min Act: -0.1700
Data Index: 535585 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3907. Min Range: -3.3907
Max Act: 3.2338. Min Act: -0.1700
Data Index: 4524914 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19