Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1302 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.4187. Min Act: -0.1700
Data Index: 6139792 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.2625. Min Act: -0.1700
Data Index: 3026119 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.2937. Min Act: -0.1700
Data Index: 2814827 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.2937. Min Act: -0.1700
Data Index: 4491399 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.2312. Min Act: -0.1700
Data Index: 7698750 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1687. Min Act: -0.1700
Data Index: 5923768 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1375. Min Act: -0.1700
Data Index: 2750598 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1375. Min Act: -0.1700
Data Index: 2279985 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1375. Min Act: -0.1700
Data Index: 340550 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1375. Min Act: -0.1700
Data Index: 1412660 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1375. Min Act: -0.1700
Data Index: 2732664 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1375. Min Act: -0.1700
Data Index: 2635884 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1375. Min Act: -0.1700
Data Index: 3293553 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1062. Min Act: -0.1700
Data Index: 1781420 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1375. Min Act: -0.1700
Data Index: 782214 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1062. Min Act: -0.1700
Data Index: 5307400 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1062. Min Act: -0.1700
Data Index: 3584103 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.1375. Min Act: -0.1700
Data Index: 3226715 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.0750. Min Act: -0.1700
Data Index: 6605970 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4187. Min Range: -5.4187
Max Act: 5.0750. Min Act: -0.1700
Data Index: 6780114 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19