Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2416 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5453. Min Range: -1.5453
Max Act: 1.5453. Min Act: -0.1700
Data Index: 5619508 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5453. Min Range: -1.5453
Max Act: 1.5366. Min Act: -0.1700
Data Index: 4416757 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5453. Min Range: -1.5453
Max Act: 1.5278. Min Act: -0.1700
Data Index: 40745 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5453. Min Range: -1.5453
Max Act: 1.5190. Min Act: -0.1700
Data Index: 5694949 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5453. Min Range: -1.5453
Max Act: 1.5190. Min Act: -0.1699
Data Index: 7318355 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5453. Min Range: -1.5453
Max Act: 1.5102. Min Act: -0.1674
Data Index: 1720651 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5453. Min Range: -1.5453
Max Act: 1.5015. Min Act: -0.1679
Data Index: 2790044 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5453. Min Range: -1.5453
Max Act: 1.5015. Min Act: -0.1662
Data Index: 36191 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5453. Min Range: -1.5453
Max Act: 1.5102. Min Act: -0.1700
Data Index: 652129 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5453. Min Range: -1.5453
Max Act: 1.4927. Min Act: -0.1700
Data Index: 3679094 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5453. Min Range: -1.5453
Max Act: 1.4927. Min Act: -0.1700
Data Index: 673464 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5453. Min Range: -1.5453
Max Act: 1.4751. Min Act: -0.1700
Data Index: 7927347 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5453. Min Range: -1.5453
Max Act: 1.4839. Min Act: -0.1700
Data Index: 6423276 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5453. Min Range: -1.5453
Max Act: 1.4751. Min Act: -0.1696
Data Index: 7177856 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5453. Min Range: -1.5453
Max Act: 1.4751. Min Act: -0.1700
Data Index: 6587143 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5453. Min Range: -1.5453
Max Act: 1.4751. Min Act: -0.1695
Data Index: 7428988 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5453. Min Range: -1.5453
Max Act: 1.4751. Min Act: -0.1682
Data Index: 1528396 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5453. Min Range: -1.5453
Max Act: 1.4751. Min Act: -0.1691
Data Index: 6155550 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5453. Min Range: -1.5453
Max Act: 1.4663. Min Act: -0.1687
Data Index: 2882140 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5453. Min Range: -1.5453
Max Act: 1.4575. Min Act: -0.1700
Data Index: 838617 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19