Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1547 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9249. Min Range: -5.9249
Max Act: 5.9249. Min Act: -0.1700
Data Index: 4936705 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9249. Min Range: -5.9249
Max Act: 5.7999. Min Act: -0.1700
Data Index: 1054101 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9249. Min Range: -5.9249
Max Act: 5.6437. Min Act: -0.1700
Data Index: 4706688 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9249. Min Range: -5.9249
Max Act: 5.6437. Min Act: -0.1700
Data Index: 6613486 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9249. Min Range: -5.9249
Max Act: 5.6124. Min Act: -0.1700
Data Index: 1912444 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9249. Min Range: -5.9249
Max Act: 5.5812. Min Act: -0.1700
Data Index: 2508136 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9249. Min Range: -5.9249
Max Act: 5.5812. Min Act: -0.1700
Data Index: 1878354 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9249. Min Range: -5.9249
Max Act: 5.5812. Min Act: -0.1700
Data Index: 7237500 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9249. Min Range: -5.9249
Max Act: 5.6124. Min Act: -0.1700
Data Index: 6268078 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9249. Min Range: -5.9249
Max Act: 5.5812. Min Act: -0.1700
Data Index: 4936699 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9249. Min Range: -5.9249
Max Act: 5.5499. Min Act: -0.1700
Data Index: 7305742 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9249. Min Range: -5.9249
Max Act: 5.4874. Min Act: -0.1700
Data Index: 7237499 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9249. Min Range: -5.9249
Max Act: 5.4562. Min Act: -0.1700
Data Index: 2325645 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9249. Min Range: -5.9249
Max Act: 5.4874. Min Act: -0.1700
Data Index: 8193302 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9249. Min Range: -5.9249
Max Act: 5.4562. Min Act: -0.1700
Data Index: 6754713 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9249. Min Range: -5.9249
Max Act: 5.4874. Min Act: -0.1700
Data Index: 7688342 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9249. Min Range: -5.9249
Max Act: 5.4562. Min Act: -0.1700
Data Index: 7606381 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9249. Min Range: -5.9249
Max Act: 5.4249. Min Act: -0.1700
Data Index: 8193306 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9249. Min Range: -5.9249
Max Act: 5.4249. Min Act: -0.1700
Data Index: 6032231 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9249. Min Range: -5.9249
Max Act: 5.4562. Min Act: -0.1700
Data Index: 3670621 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19