Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 922 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7340. Min Range: -7.7340
Max Act: 7.7340. Min Act: -0.1700
Data Index: 1660599 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7340. Min Range: -7.7340
Max Act: 7.3903. Min Act: -0.1700
Data Index: 3665208 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7340. Min Range: -7.7340
Max Act: 7.3278. Min Act: -0.1700
Data Index: 8663955 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7340. Min Range: -7.7340
Max Act: 7.2340. Min Act: -0.1700
Data Index: 4995553 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7340. Min Range: -7.7340
Max Act: 7.2028. Min Act: -0.1700
Data Index: 1503569 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7340. Min Range: -7.7340
Max Act: 7.1715. Min Act: -0.1700
Data Index: 1068402 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7340. Min Range: -7.7340
Max Act: 7.1715. Min Act: -0.1700
Data Index: 4083778 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7340. Min Range: -7.7340
Max Act: 7.1090. Min Act: -0.1700
Data Index: 424388 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7340. Min Range: -7.7340
Max Act: 7.0153. Min Act: -0.1700
Data Index: 6202644 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7340. Min Range: -7.7340
Max Act: 6.9840. Min Act: -0.1700
Data Index: 7806257 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7340. Min Range: -7.7340
Max Act: 6.8903. Min Act: -0.1700
Data Index: 8734427 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7340. Min Range: -7.7340
Max Act: 6.8903. Min Act: -0.1700
Data Index: 6125079 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7340. Min Range: -7.7340
Max Act: 6.8903. Min Act: -0.1700
Data Index: 4121470 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7340. Min Range: -7.7340
Max Act: 6.8590. Min Act: -0.1700
Data Index: 6747771 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7340. Min Range: -7.7340
Max Act: 6.8590. Min Act: -0.1700
Data Index: 7492339 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7340. Min Range: -7.7340
Max Act: 6.7965. Min Act: -0.1700
Data Index: 6060536 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7340. Min Range: -7.7340
Max Act: 6.7965. Min Act: -0.1700
Data Index: 5485567 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7340. Min Range: -7.7340
Max Act: 6.7653. Min Act: -0.1700
Data Index: 5918030 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7340. Min Range: -7.7340
Max Act: 6.7653. Min Act: -0.1700
Data Index: 5909503 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7340. Min Range: -7.7340
Max Act: 6.7653. Min Act: -0.1700
Data Index: 7289390 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19