Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 893 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9767. Min Range: -0.9767
Max Act: 0.9767. Min Act: -0.1700
Data Index: 3984720 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9767. Min Range: -0.9767
Max Act: 0.9422. Min Act: -0.1700
Data Index: 3263120 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9767. Min Range: -0.9767
Max Act: 0.9164. Min Act: -0.1700
Data Index: 8426276 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9767. Min Range: -0.9767
Max Act: 0.9078. Min Act: -0.1700
Data Index: 3188347 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9767. Min Range: -0.9767
Max Act: 0.8992. Min Act: -0.1700
Data Index: 2984863 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9767. Min Range: -0.9767
Max Act: 0.8907. Min Act: -0.1700
Data Index: 6716444 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9767. Min Range: -0.9767
Max Act: 0.8822. Min Act: -0.1700
Data Index: 3343346 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9767. Min Range: -0.9767
Max Act: 0.8736. Min Act: -0.1700
Data Index: 902807 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9767. Min Range: -0.9767
Max Act: 0.8651. Min Act: -0.1700
Data Index: 3086780 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9767. Min Range: -0.9767
Max Act: 0.8651. Min Act: -0.1700
Data Index: 2923347 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9767. Min Range: -0.9767
Max Act: 0.8651. Min Act: -0.1700
Data Index: 7078087 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9767. Min Range: -0.9767
Max Act: 0.8651. Min Act: -0.1700
Data Index: 5621203 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9767. Min Range: -0.9767
Max Act: 0.8566. Min Act: -0.1700
Data Index: 3184421 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9767. Min Range: -0.9767
Max Act: 0.8482. Min Act: -0.1700
Data Index: 923362 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9767. Min Range: -0.9767
Max Act: 0.8482. Min Act: -0.1700
Data Index: 1181714 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9767. Min Range: -0.9767
Max Act: 0.8397. Min Act: -0.1700
Data Index: 7333580 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9767. Min Range: -0.9767
Max Act: 0.8397. Min Act: -0.1700
Data Index: 8651444 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9767. Min Range: -0.9767
Max Act: 0.8397. Min Act: -0.1700
Data Index: 7045129 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9767. Min Range: -0.9767
Max Act: 0.8397. Min Act: -0.1700
Data Index: 6350297 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9767. Min Range: -0.9767
Max Act: 0.8312. Min Act: -0.1700
Data Index: 3723306 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19