Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3034 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6118. Min Range: -3.6118
Max Act: 3.6118. Min Act: -0.1700
Data Index: 190962 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6118. Min Range: -3.6118
Max Act: 3.5962. Min Act: -0.1700
Data Index: 2602839 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6118. Min Range: -3.6118
Max Act: 3.5649. Min Act: -0.1700
Data Index: 1717556 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6118. Min Range: -3.6118
Max Act: 3.5336. Min Act: -0.1700
Data Index: 3336827 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6118. Min Range: -3.6118
Max Act: 3.4709. Min Act: -0.1700
Data Index: 3336828 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6118. Min Range: -3.6118
Max Act: 3.4709. Min Act: -0.1700
Data Index: 5234901 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6118. Min Range: -3.6118
Max Act: 3.5022. Min Act: -0.1700
Data Index: 8570550 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6118. Min Range: -3.6118
Max Act: 3.4709. Min Act: -0.1700
Data Index: 6779249 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6118. Min Range: -3.6118
Max Act: 3.4709. Min Act: -0.1700
Data Index: 398289 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6118. Min Range: -3.6118
Max Act: 3.4553. Min Act: -0.1700
Data Index: 2655070 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6118. Min Range: -3.6118
Max Act: 3.4553. Min Act: -0.1700
Data Index: 1613701 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6118. Min Range: -3.6118
Max Act: 3.4396. Min Act: -0.1700
Data Index: 4667214 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6118. Min Range: -3.6118
Max Act: 3.4239. Min Act: -0.1700
Data Index: 1738410 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6118. Min Range: -3.6118
Max Act: 3.4239. Min Act: -0.1700
Data Index: 6404807 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6118. Min Range: -3.6118
Max Act: 3.4239. Min Act: -0.1700
Data Index: 5440341 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6118. Min Range: -3.6118
Max Act: 3.4082. Min Act: -0.1700
Data Index: 6118283 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6118. Min Range: -3.6118
Max Act: 3.4082. Min Act: -0.1700
Data Index: 6783257 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6118. Min Range: -3.6118
Max Act: 3.3926. Min Act: -0.1700
Data Index: 6228195 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6118. Min Range: -3.6118
Max Act: 3.4082. Min Act: -0.1700
Data Index: 3520397 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6118. Min Range: -3.6118
Max Act: 3.3926. Min Act: -0.1700
Data Index: 6324795 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19