Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1746 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0790. Min Range: -4.0790
Max Act: 4.0790. Min Act: -0.1700
Data Index: 6575779 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0790. Min Range: -4.0790
Max Act: 4.0790. Min Act: -0.1700
Data Index: 4581788 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0790. Min Range: -4.0790
Max Act: 4.0790. Min Act: -0.1700
Data Index: 8157878 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0790. Min Range: -4.0790
Max Act: 4.0477. Min Act: -0.1700
Data Index: 4320924 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0790. Min Range: -4.0790
Max Act: 4.0477. Min Act: -0.1700
Data Index: 8060589 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0790. Min Range: -4.0790
Max Act: 4.0477. Min Act: -0.1700
Data Index: 4175868 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0790. Min Range: -4.0790
Max Act: 4.0165. Min Act: -0.1700
Data Index: 3382538 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0790. Min Range: -4.0790
Max Act: 4.0477. Min Act: -0.1700
Data Index: 1635424 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0790. Min Range: -4.0790
Max Act: 4.0165. Min Act: -0.1700
Data Index: 5596079 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0790. Min Range: -4.0790
Max Act: 4.0165. Min Act: -0.1700
Data Index: 2580174 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0790. Min Range: -4.0790
Max Act: 4.0165. Min Act: -0.1700
Data Index: 774485 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0790. Min Range: -4.0790
Max Act: 4.0165. Min Act: -0.1700
Data Index: 3824700 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0790. Min Range: -4.0790
Max Act: 4.0165. Min Act: -0.1700
Data Index: 1236853 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0790. Min Range: -4.0790
Max Act: 4.0165. Min Act: -0.1700
Data Index: 1199797 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0790. Min Range: -4.0790
Max Act: 4.0165. Min Act: -0.1700
Data Index: 3261323 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0790. Min Range: -4.0790
Max Act: 3.9852. Min Act: -0.1700
Data Index: 3238732 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0790. Min Range: -4.0790
Max Act: 4.0165. Min Act: -0.1700
Data Index: 521305 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0790. Min Range: -4.0790
Max Act: 4.0165. Min Act: -0.1700
Data Index: 7507592 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0790. Min Range: -4.0790
Max Act: 4.0165. Min Act: -0.1700
Data Index: 3210053 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0790. Min Range: -4.0790
Max Act: 3.9852. Min Act: -0.1700
Data Index: 4161395 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19