Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1611. Min Range: -5.1611
Max Act: 5.1611. Min Act: -0.1700
Data Index: 257294 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1611. Min Range: -5.1611
Max Act: 5.0986. Min Act: -0.1700
Data Index: 3467617 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1611. Min Range: -5.1611
Max Act: 5.0049. Min Act: -0.1700
Data Index: 3212217 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1611. Min Range: -5.1611
Max Act: 5.0049. Min Act: -0.1700
Data Index: 598043 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1611. Min Range: -5.1611
Max Act: 4.9736. Min Act: -0.1700
Data Index: 6846939 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1611. Min Range: -5.1611
Max Act: 4.9424. Min Act: -0.1700
Data Index: 6611268 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1611. Min Range: -5.1611
Max Act: 4.9424. Min Act: -0.1700
Data Index: 875588 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1611. Min Range: -5.1611
Max Act: 4.9424. Min Act: -0.1698
Data Index: 2634844 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1611. Min Range: -5.1611
Max Act: 4.9424. Min Act: -0.1700
Data Index: 7181235 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1611. Min Range: -5.1611
Max Act: 4.9111. Min Act: -0.1700
Data Index: 2269912 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1611. Min Range: -5.1611
Max Act: 4.8799. Min Act: -0.1700
Data Index: 584475 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1611. Min Range: -5.1611
Max Act: 4.8799. Min Act: -0.1700
Data Index: 2419174 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1611. Min Range: -5.1611
Max Act: 4.8799. Min Act: -0.1700
Data Index: 1050297 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1611. Min Range: -5.1611
Max Act: 4.8799. Min Act: -0.1700
Data Index: 3879675 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1611. Min Range: -5.1611
Max Act: 4.8799. Min Act: -0.1700
Data Index: 3059784 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1611. Min Range: -5.1611
Max Act: 4.8799. Min Act: -0.1700
Data Index: 2993763 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1611. Min Range: -5.1611
Max Act: 4.8799. Min Act: -0.1700
Data Index: 1328851 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1611. Min Range: -5.1611
Max Act: 4.8799. Min Act: -0.1700
Data Index: 881794 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1611. Min Range: -5.1611
Max Act: 4.8486. Min Act: -0.1700
Data Index: 1059151 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1611. Min Range: -5.1611
Max Act: 4.8486. Min Act: -0.1700
Data Index: 4913283 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19