Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5942 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3366. Min Range: -3.3366
Max Act: 3.3366. Min Act: -0.1700
Data Index: 5259995 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3366. Min Range: -3.3366
Max Act: 3.3366. Min Act: -0.1700
Data Index: 8216817 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3366. Min Range: -3.3366
Max Act: 3.3366. Min Act: -0.1700
Data Index: 3599542 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3366. Min Range: -3.3366
Max Act: 3.3366. Min Act: -0.1700
Data Index: 7248963 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3366. Min Range: -3.3366
Max Act: 3.3366. Min Act: -0.1700
Data Index: 5780139 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3366. Min Range: -3.3366
Max Act: 3.3052. Min Act: -0.1700
Data Index: 3587370 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3366. Min Range: -3.3366
Max Act: 3.3052. Min Act: -0.1700
Data Index: 712884 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3366. Min Range: -3.3366
Max Act: 3.3052. Min Act: -0.1700
Data Index: 5288177 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3366. Min Range: -3.3366
Max Act: 3.3052. Min Act: -0.1700
Data Index: 7440679 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3366. Min Range: -3.3366
Max Act: 3.3052. Min Act: -0.1700
Data Index: 4198681 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3366. Min Range: -3.3366
Max Act: 3.3052. Min Act: -0.1700
Data Index: 7774499 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3366. Min Range: -3.3366
Max Act: 3.3052. Min Act: -0.1700
Data Index: 4759859 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3366. Min Range: -3.3366
Max Act: 3.3052. Min Act: -0.1700
Data Index: 96327 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3366. Min Range: -3.3366
Max Act: 3.2895. Min Act: -0.1700
Data Index: 753216 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3366. Min Range: -3.3366
Max Act: 3.2895. Min Act: -0.1700
Data Index: 846082 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3366. Min Range: -3.3366
Max Act: 3.2895. Min Act: -0.1700
Data Index: 1956157 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3366. Min Range: -3.3366
Max Act: 3.2895. Min Act: -0.1700
Data Index: 2965118 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3366. Min Range: -3.3366
Max Act: 3.2895. Min Act: -0.1700
Data Index: 7610037 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3366. Min Range: -3.3366
Max Act: 3.2895. Min Act: -0.1700
Data Index: 2539516 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3366. Min Range: -3.3366
Max Act: 3.2738. Min Act: -0.1700
Data Index: 2896326 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19