Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2144 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.8551. Min Act: -0.1700
Data Index: 935129 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.8238. Min Act: -0.1700
Data Index: 1172879 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.8238. Min Act: -0.1700
Data Index: 1624127 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.7925. Min Act: -0.1700
Data Index: 477942 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.7925. Min Act: -0.1700
Data Index: 1707334 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.7925. Min Act: -0.1700
Data Index: 7267341 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.7300. Min Act: -0.1700
Data Index: 645819 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.7613. Min Act: -0.1700
Data Index: 6274437 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.7613. Min Act: -0.1700
Data Index: 4063624 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.7613. Min Act: -0.1700
Data Index: 7279435 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.7300. Min Act: -0.1700
Data Index: 5510610 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.7300. Min Act: -0.1700
Data Index: 5232962 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.7300. Min Act: -0.1700
Data Index: 217424 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.7300. Min Act: -0.1700
Data Index: 560569 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.7300. Min Act: -0.1700
Data Index: 4192441 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.7300. Min Act: -0.1700
Data Index: 6266260 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.6987. Min Act: -0.1700
Data Index: 4860499 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.6987. Min Act: -0.1700
Data Index: 337499 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.6987. Min Act: -0.1700
Data Index: 2562095 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8551. Min Range: -3.8551
Max Act: 3.6987. Min Act: -0.1700
Data Index: 2191069 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19