Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1966 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1303. Min Range: -5.1303
Max Act: 5.1303. Min Act: -0.1700
Data Index: 6756526 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1303. Min Range: -5.1303
Max Act: 5.0053. Min Act: -0.1700
Data Index: 665507 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1303. Min Range: -5.1303
Max Act: 4.9428. Min Act: -0.1700
Data Index: 5505614 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1303. Min Range: -5.1303
Max Act: 4.8803. Min Act: -0.1700
Data Index: 3075714 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1303. Min Range: -5.1303
Max Act: 4.9116. Min Act: -0.1700
Data Index: 8176559 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1303. Min Range: -5.1303
Max Act: 4.8803. Min Act: -0.1700
Data Index: 2665352 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1303. Min Range: -5.1303
Max Act: 4.8491. Min Act: -0.1700
Data Index: 3415559 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1303. Min Range: -5.1303
Max Act: 4.8491. Min Act: -0.1700
Data Index: 4569040 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1303. Min Range: -5.1303
Max Act: 4.8178. Min Act: -0.1700
Data Index: 7907101 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1303. Min Range: -5.1303
Max Act: 4.8178. Min Act: -0.1700
Data Index: 5023000 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1303. Min Range: -5.1303
Max Act: 4.8178. Min Act: -0.1700
Data Index: 7654376 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1303. Min Range: -5.1303
Max Act: 4.7866. Min Act: -0.1700
Data Index: 6260602 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1303. Min Range: -5.1303
Max Act: 4.7866. Min Act: -0.1700
Data Index: 1021800 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1303. Min Range: -5.1303
Max Act: 4.7866. Min Act: -0.1700
Data Index: 4668504 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1303. Min Range: -5.1303
Max Act: 4.7553. Min Act: -0.1700
Data Index: 5301742 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1303. Min Range: -5.1303
Max Act: 4.7553. Min Act: -0.1700
Data Index: 206797 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1303. Min Range: -5.1303
Max Act: 4.7553. Min Act: -0.1700
Data Index: 7315154 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1303. Min Range: -5.1303
Max Act: 4.7553. Min Act: -0.1700
Data Index: 4158034 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1303. Min Range: -5.1303
Max Act: 4.7553. Min Act: -0.1700
Data Index: 2503171 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1303. Min Range: -5.1303
Max Act: 4.7241. Min Act: -0.1700
Data Index: 775793 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19