Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1307 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6529. Min Range: -4.6529
Max Act: 4.6529. Min Act: -0.1700
Data Index: 1651290 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6529. Min Range: -4.6529
Max Act: 4.4654. Min Act: -0.1700
Data Index: 1598641 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6529. Min Range: -4.6529
Max Act: 4.5279. Min Act: -0.1700
Data Index: 528650 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6529. Min Range: -4.6529
Max Act: 4.4341. Min Act: -0.1700
Data Index: 3443045 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6529. Min Range: -4.6529
Max Act: 4.4654. Min Act: -0.1700
Data Index: 2241207 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6529. Min Range: -4.6529
Max Act: 4.4654. Min Act: -0.1700
Data Index: 4035029 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6529. Min Range: -4.6529
Max Act: 4.4654. Min Act: -0.1700
Data Index: 2500738 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6529. Min Range: -4.6529
Max Act: 4.4654. Min Act: -0.1700
Data Index: 1142832 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6529. Min Range: -4.6529
Max Act: 4.4654. Min Act: -0.1700
Data Index: 6464001 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6529. Min Range: -4.6529
Max Act: 4.4654. Min Act: -0.1700
Data Index: 6303002 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6529. Min Range: -4.6529
Max Act: 4.4654. Min Act: -0.1700
Data Index: 2516745 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6529. Min Range: -4.6529
Max Act: 4.4654. Min Act: -0.1700
Data Index: 270363 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6529. Min Range: -4.6529
Max Act: 4.4654. Min Act: -0.1700
Data Index: 1761377 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6529. Min Range: -4.6529
Max Act: 4.4654. Min Act: -0.1700
Data Index: 1105832 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6529. Min Range: -4.6529
Max Act: 4.4654. Min Act: -0.1700
Data Index: 3387968 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6529. Min Range: -4.6529
Max Act: 4.4654. Min Act: -0.1700
Data Index: 2045529 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6529. Min Range: -4.6529
Max Act: 4.4028. Min Act: -0.1700
Data Index: 2967354 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6529. Min Range: -4.6529
Max Act: 4.4654. Min Act: -0.1700
Data Index: 3039336 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6529. Min Range: -4.6529
Max Act: 4.4654. Min Act: -0.1700
Data Index: 4268411 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6529. Min Range: -4.6529
Max Act: 4.4654. Min Act: -0.1700
Data Index: 4831487 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19