Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3418 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6174. Min Range: -1.6174
Max Act: 1.6174. Min Act: -0.1690
Data Index: 7827151 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6174. Min Range: -1.6174
Max Act: 1.5475. Min Act: -0.1700
Data Index: 2678942 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6174. Min Range: -1.6174
Max Act: 1.5475. Min Act: -0.1700
Data Index: 2501812 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6174. Min Range: -1.6174
Max Act: 1.5387. Min Act: -0.1700
Data Index: 7036369 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6174. Min Range: -1.6174
Max Act: 1.5212. Min Act: -0.1700
Data Index: 7159871 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6174. Min Range: -1.6174
Max Act: 1.5212. Min Act: -0.1700
Data Index: 4851464 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6174. Min Range: -1.6174
Max Act: 1.5212. Min Act: -0.1700
Data Index: 1462614 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6174. Min Range: -1.6174
Max Act: 1.5124. Min Act: -0.1699
Data Index: 6328955 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6174. Min Range: -1.6174
Max Act: 1.5212. Min Act: -0.1700
Data Index: 751783 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6174. Min Range: -1.6174
Max Act: 1.5212. Min Act: -0.1700
Data Index: 4849271 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6174. Min Range: -1.6174
Max Act: 1.5212. Min Act: -0.1700
Data Index: 1601268 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6174. Min Range: -1.6174
Max Act: 1.5037. Min Act: -0.1691
Data Index: 7488986 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6174. Min Range: -1.6174
Max Act: 1.5124. Min Act: -0.1700
Data Index: 3525100 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6174. Min Range: -1.6174
Max Act: 1.5037. Min Act: -0.1700
Data Index: 7344639 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6174. Min Range: -1.6174
Max Act: 1.5124. Min Act: -0.1700
Data Index: 6885279 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6174. Min Range: -1.6174
Max Act: 1.5124. Min Act: -0.1700
Data Index: 1202066 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6174. Min Range: -1.6174
Max Act: 1.4949. Min Act: -0.1691
Data Index: 2475445 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6174. Min Range: -1.6174
Max Act: 1.5037. Min Act: -0.1700
Data Index: 8080277 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6174. Min Range: -1.6174
Max Act: 1.4949. Min Act: -0.1700
Data Index: 2585998 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6174. Min Range: -1.6174
Max Act: 1.4949. Min Act: -0.1700
Data Index: 782961 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19