Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1514 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5226. Min Range: -1.5226
Max Act: 1.5226. Min Act: -0.1699
Data Index: 3563696 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5226. Min Range: -1.5226
Max Act: 1.4875. Min Act: -0.1700
Data Index: 7954277 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5226. Min Range: -1.5226
Max Act: 1.4700. Min Act: -0.1697
Data Index: 4859665 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5226. Min Range: -1.5226
Max Act: 1.4524. Min Act: -0.1700
Data Index: 6471557 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5226. Min Range: -1.5226
Max Act: 1.4260. Min Act: -0.1700
Data Index: 1212482 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5226. Min Range: -1.5226
Max Act: 1.4172. Min Act: -0.1700
Data Index: 289491 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5226. Min Range: -1.5226
Max Act: 1.3996. Min Act: -0.1700
Data Index: 5559318 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5226. Min Range: -1.5226
Max Act: 1.4172. Min Act: -0.1700
Data Index: 3378624 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5226. Min Range: -1.5226
Max Act: 1.4084. Min Act: -0.1700
Data Index: 4002058 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5226. Min Range: -1.5226
Max Act: 1.4084. Min Act: -0.1700
Data Index: 1495898 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5226. Min Range: -1.5226
Max Act: 1.3907. Min Act: -0.1700
Data Index: 8525420 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5226. Min Range: -1.5226
Max Act: 1.3996. Min Act: -0.1700
Data Index: 3522498 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5226. Min Range: -1.5226
Max Act: 1.3819. Min Act: -0.1700
Data Index: 8648581 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5226. Min Range: -1.5226
Max Act: 1.3819. Min Act: -0.1700
Data Index: 2140675 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5226. Min Range: -1.5226
Max Act: 1.3731. Min Act: -0.1700
Data Index: 2463183 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5226. Min Range: -1.5226
Max Act: 1.3819. Min Act: -0.1700
Data Index: 7405201 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5226. Min Range: -1.5226
Max Act: 1.3643. Min Act: -0.1700
Data Index: 8822894 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5226. Min Range: -1.5226
Max Act: 1.3555. Min Act: -0.1700
Data Index: 1368357 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5226. Min Range: -1.5226
Max Act: 1.3731. Min Act: -0.1700
Data Index: 6551763 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5226. Min Range: -1.5226
Max Act: 1.3643. Min Act: -0.1700
Data Index: 3283200 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19