Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2597 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.5918. Min Act: -0.1700
Data Index: 3525637 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.4822. Min Act: -0.1700
Data Index: 1351870 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.2783. Min Act: -0.1700
Data Index: 4441285 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.2312. Min Act: -0.1700
Data Index: 8617573 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.2312. Min Act: -0.1700
Data Index: 5360170 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.1840. Min Act: -0.1700
Data Index: 1135750 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.1683. Min Act: -0.1700
Data Index: 2235324 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.1683. Min Act: -0.1700
Data Index: 5411217 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.1840. Min Act: -0.1700
Data Index: 1505240 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.1526. Min Act: -0.1700
Data Index: 237774 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.1683. Min Act: -0.1700
Data Index: 3234515 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.1211. Min Act: -0.1700
Data Index: 2611403 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.1368. Min Act: -0.1700
Data Index: 3429417 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.1368. Min Act: -0.1700
Data Index: 6180046 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.1368. Min Act: -0.1700
Data Index: 6578826 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.1211. Min Act: -0.1700
Data Index: 830638 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.1211. Min Act: -0.1700
Data Index: 2462892 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.1053. Min Act: -0.1700
Data Index: 7300563 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.1211. Min Act: -0.1700
Data Index: 6304692 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.1053. Min Act: -0.1700
Data Index: 6339812 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19