Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3503 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2419. Min Range: -5.2419
Max Act: 5.2419. Min Act: -0.1700
Data Index: 6657775 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2419. Min Range: -5.2419
Max Act: 5.2419. Min Act: -0.1700
Data Index: 8332220 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2419. Min Range: -5.2419
Max Act: 5.2106. Min Act: -0.1700
Data Index: 5180610 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2419. Min Range: -5.2419
Max Act: 5.2106. Min Act: -0.1700
Data Index: 3774758 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2419. Min Range: -5.2419
Max Act: 5.1481. Min Act: -0.1700
Data Index: 1676375 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2419. Min Range: -5.2419
Max Act: 5.1481. Min Act: -0.1700
Data Index: 5782657 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2419. Min Range: -5.2419
Max Act: 5.0856. Min Act: -0.1700
Data Index: 3838421 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2419. Min Range: -5.2419
Max Act: 5.0856. Min Act: -0.1700
Data Index: 4182646 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2419. Min Range: -5.2419
Max Act: 5.0544. Min Act: -0.1700
Data Index: 794937 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2419. Min Range: -5.2419
Max Act: 5.0544. Min Act: -0.1700
Data Index: 7566007 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2419. Min Range: -5.2419
Max Act: 5.0544. Min Act: -0.1700
Data Index: 1267705 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2419. Min Range: -5.2419
Max Act: 5.0856. Min Act: -0.1700
Data Index: 1724446 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2419. Min Range: -5.2419
Max Act: 5.0544. Min Act: -0.1700
Data Index: 595206 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2419. Min Range: -5.2419
Max Act: 5.0231. Min Act: -0.1700
Data Index: 3320195 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2419. Min Range: -5.2419
Max Act: 5.0544. Min Act: -0.1700
Data Index: 3835447 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2419. Min Range: -5.2419
Max Act: 4.9919. Min Act: -0.1700
Data Index: 4182645 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2419. Min Range: -5.2419
Max Act: 4.9606. Min Act: -0.1700
Data Index: 6071389 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2419. Min Range: -5.2419
Max Act: 4.9606. Min Act: -0.1700
Data Index: 3158398 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2419. Min Range: -5.2419
Max Act: 4.9606. Min Act: -0.1700
Data Index: 1932545 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2419. Min Range: -5.2419
Max Act: 4.9606. Min Act: -0.1700
Data Index: 3299488 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19