Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5321 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8701. Min Range: -3.8701
Max Act: 3.8701. Min Act: -0.1700
Data Index: 5007497 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8701. Min Range: -3.8701
Max Act: 3.8388. Min Act: -0.1700
Data Index: 2502273 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8701. Min Range: -3.8701
Max Act: 3.7294. Min Act: -0.1700
Data Index: 6383934 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8701. Min Range: -3.8701
Max Act: 3.7137. Min Act: -0.1700
Data Index: 1649411 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8701. Min Range: -3.8701
Max Act: 3.7137. Min Act: -0.1700
Data Index: 7578942 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8701. Min Range: -3.8701
Max Act: 3.7294. Min Act: -0.1700
Data Index: 2753612 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8701. Min Range: -3.8701
Max Act: 3.6825. Min Act: -0.1700
Data Index: 5787143 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8701. Min Range: -3.8701
Max Act: 3.6668. Min Act: -0.1700
Data Index: 7385287 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8701. Min Range: -3.8701
Max Act: 3.6512. Min Act: -0.1700
Data Index: 6381811 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8701. Min Range: -3.8701
Max Act: 3.6512. Min Act: -0.1700
Data Index: 3141666 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8701. Min Range: -3.8701
Max Act: 3.6355. Min Act: -0.1700
Data Index: 198718 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8701. Min Range: -3.8701
Max Act: 3.6512. Min Act: -0.1700
Data Index: 4952937 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8701. Min Range: -3.8701
Max Act: 3.6355. Min Act: -0.1700
Data Index: 7989790 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8701. Min Range: -3.8701
Max Act: 3.6199. Min Act: -0.1700
Data Index: 6007573 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8701. Min Range: -3.8701
Max Act: 3.6042. Min Act: -0.1700
Data Index: 8566951 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8701. Min Range: -3.8701
Max Act: 3.6042. Min Act: -0.1700
Data Index: 8568958 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8701. Min Range: -3.8701
Max Act: 3.5729. Min Act: -0.1700
Data Index: 5857686 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8701. Min Range: -3.8701
Max Act: 3.5886. Min Act: -0.1700
Data Index: 6501367 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8701. Min Range: -3.8701
Max Act: 3.5886. Min Act: -0.1700
Data Index: 116959 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8701. Min Range: -3.8701
Max Act: 3.5729. Min Act: -0.1700
Data Index: 7574862 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19