Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2405 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1008. Min Range: -7.1008
Max Act: 7.1008. Min Act: -0.1700
Data Index: 243821 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1008. Min Range: -7.1008
Max Act: 6.8821. Min Act: -0.1700
Data Index: 2679578 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1008. Min Range: -7.1008
Max Act: 6.7883. Min Act: -0.1700
Data Index: 6075171 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1008. Min Range: -7.1008
Max Act: 6.7258. Min Act: -0.1700
Data Index: 40740 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1008. Min Range: -7.1008
Max Act: 6.7571. Min Act: -0.1700
Data Index: 2087995 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1008. Min Range: -7.1008
Max Act: 6.6946. Min Act: -0.1700
Data Index: 6755327 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1008. Min Range: -7.1008
Max Act: 6.6321. Min Act: -0.1700
Data Index: 7227952 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1008. Min Range: -7.1008
Max Act: 6.6008. Min Act: -0.1700
Data Index: 8110594 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1008. Min Range: -7.1008
Max Act: 6.5383. Min Act: -0.1700
Data Index: 4064083 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1008. Min Range: -7.1008
Max Act: 6.5071. Min Act: -0.1700
Data Index: 161309 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1008. Min Range: -7.1008
Max Act: 6.4446. Min Act: -0.1700
Data Index: 1549907 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1008. Min Range: -7.1008
Max Act: 6.4133. Min Act: -0.1700
Data Index: 8572400 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1008. Min Range: -7.1008
Max Act: 6.2883. Min Act: -0.1700
Data Index: 6543726 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1008. Min Range: -7.1008
Max Act: 6.2883. Min Act: -0.1700
Data Index: 3389352 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1008. Min Range: -7.1008
Max Act: 6.2571. Min Act: -0.1700
Data Index: 1791720 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1008. Min Range: -7.1008
Max Act: 6.2571. Min Act: -0.1700
Data Index: 3871653 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1008. Min Range: -7.1008
Max Act: 6.1946. Min Act: -0.1700
Data Index: 1791712 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1008. Min Range: -7.1008
Max Act: 6.1946. Min Act: -0.1700
Data Index: 5061722 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1008. Min Range: -7.1008
Max Act: 6.1633. Min Act: -0.1700
Data Index: 7220506 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1008. Min Range: -7.1008
Max Act: 6.1946. Min Act: -0.1700
Data Index: 7706946 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19