Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 141 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6571. Min Range: -5.6571
Max Act: 3.7819. Min Act: -0.1700
Data Index: 8036152 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6571. Min Range: -5.6571
Max Act: 5.5634. Min Act: -0.1700
Data Index: 4667493 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6571. Min Range: -5.6571
Max Act: 5.6571. Min Act: -0.1700
Data Index: 4100984 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6571. Min Range: -5.6571
Max Act: 5.6259. Min Act: -0.1700
Data Index: 6255375 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6571. Min Range: -5.6571
Max Act: 5.5946. Min Act: -0.1700
Data Index: 2150295 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6571. Min Range: -5.6571
Max Act: 5.6259. Min Act: -0.1700
Data Index: 4121057 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6571. Min Range: -5.6571
Max Act: 5.6259. Min Act: -0.1700
Data Index: 6026156 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6571. Min Range: -5.6571
Max Act: 5.5009. Min Act: -0.1700
Data Index: 2240098 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6571. Min Range: -5.6571
Max Act: 5.1884. Min Act: -0.1700
Data Index: 4490756 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6571. Min Range: -5.6571
Max Act: 5.4384. Min Act: -0.1700
Data Index: 8061120 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6571. Min Range: -5.6571
Max Act: 5.4696. Min Act: -0.1700
Data Index: 6053803 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6571. Min Range: -5.6571
Max Act: 5.5009. Min Act: -0.1700
Data Index: 7729392 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6571. Min Range: -5.6571
Max Act: 5.4384. Min Act: -0.1700
Data Index: 5487143 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6571. Min Range: -5.6571
Max Act: 5.3446. Min Act: -0.1700
Data Index: 2005748 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6571. Min Range: -5.6571
Max Act: 5.3446. Min Act: -0.1695
Data Index: 2304620 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6571. Min Range: -5.6571
Max Act: 4.3915. Min Act: -0.1700
Data Index: 227744 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6571. Min Range: -5.6571
Max Act: 5.2821. Min Act: -0.1700
Data Index: 2656534 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6571. Min Range: -5.6571
Max Act: 5.3134. Min Act: -0.1700
Data Index: 6106075 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6571. Min Range: -5.6571
Max Act: 4.8759. Min Act: -0.1700
Data Index: 635548 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6571. Min Range: -5.6571
Max Act: 5.2509. Min Act: -0.1700
Data Index: 5007217 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19