Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6131. Min Range: -6.6131
Max Act: 6.6131. Min Act: -0.1700
Data Index: 4080412 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6131. Min Range: -6.6131
Max Act: 6.6131. Min Act: -0.1700
Data Index: 6991908 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6131. Min Range: -6.6131
Max Act: 6.6131. Min Act: -0.1700
Data Index: 5315039 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6131. Min Range: -6.6131
Max Act: 6.5506. Min Act: -0.1700
Data Index: 8796810 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6131. Min Range: -6.6131
Max Act: 6.5819. Min Act: -0.1700
Data Index: 8621244 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6131. Min Range: -6.6131
Max Act: 6.4881. Min Act: -0.1700
Data Index: 1951436 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6131. Min Range: -6.6131
Max Act: 6.5194. Min Act: -0.1700
Data Index: 334820 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6131. Min Range: -6.6131
Max Act: 6.4881. Min Act: -0.1700
Data Index: 6552486 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6131. Min Range: -6.6131
Max Act: 6.4881. Min Act: -0.1700
Data Index: 8564513 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6131. Min Range: -6.6131
Max Act: 6.4569. Min Act: -0.1700
Data Index: 4212552 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6131. Min Range: -6.6131
Max Act: 6.4881. Min Act: -0.1700
Data Index: 6621042 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6131. Min Range: -6.6131
Max Act: 6.4256. Min Act: -0.1700
Data Index: 7863311 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6131. Min Range: -6.6131
Max Act: 6.4256. Min Act: -0.1700
Data Index: 4957997 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6131. Min Range: -6.6131
Max Act: 6.3944. Min Act: -0.1700
Data Index: 3879567 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6131. Min Range: -6.6131
Max Act: 6.3631. Min Act: -0.1700
Data Index: 700376 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6131. Min Range: -6.6131
Max Act: 6.3631. Min Act: -0.1700
Data Index: 8257826 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6131. Min Range: -6.6131
Max Act: 6.3006. Min Act: -0.1700
Data Index: 8399138 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6131. Min Range: -6.6131
Max Act: 6.3006. Min Act: -0.1700
Data Index: 5000914 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6131. Min Range: -6.6131
Max Act: 6.3006. Min Act: -0.1700
Data Index: 4806973 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6131. Min Range: -6.6131
Max Act: 6.2694. Min Act: -0.1700
Data Index: 963490 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19