Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2993 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4176. Min Range: -7.4176
Max Act: 7.4176. Min Act: -0.1700
Data Index: 4270218 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4176. Min Range: -7.4176
Max Act: 7.0739. Min Act: -0.1700
Data Index: 5261408 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4176. Min Range: -7.4176
Max Act: 6.9801. Min Act: -0.1700
Data Index: 8518959 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4176. Min Range: -7.4176
Max Act: 6.9489. Min Act: -0.1700
Data Index: 8073479 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4176. Min Range: -7.4176
Max Act: 6.9489. Min Act: -0.1700
Data Index: 4184441 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4176. Min Range: -7.4176
Max Act: 6.9489. Min Act: -0.1700
Data Index: 3966731 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4176. Min Range: -7.4176
Max Act: 6.8551. Min Act: -0.1700
Data Index: 7799669 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4176. Min Range: -7.4176
Max Act: 6.8551. Min Act: -0.1700
Data Index: 8409015 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4176. Min Range: -7.4176
Max Act: 6.8239. Min Act: -0.1700
Data Index: 3966730 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4176. Min Range: -7.4176
Max Act: 6.7926. Min Act: -0.1700
Data Index: 5601175 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4176. Min Range: -7.4176
Max Act: 6.7614. Min Act: -0.1700
Data Index: 2256118 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4176. Min Range: -7.4176
Max Act: 6.7301. Min Act: -0.1700
Data Index: 7505315 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4176. Min Range: -7.4176
Max Act: 6.7301. Min Act: -0.1700
Data Index: 5233693 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4176. Min Range: -7.4176
Max Act: 6.7301. Min Act: -0.1700
Data Index: 1799058 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4176. Min Range: -7.4176
Max Act: 6.7301. Min Act: -0.1700
Data Index: 2672591 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4176. Min Range: -7.4176
Max Act: 6.6989. Min Act: -0.1700
Data Index: 2443654 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4176. Min Range: -7.4176
Max Act: 6.6676. Min Act: -0.1700
Data Index: 6108691 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4176. Min Range: -7.4176
Max Act: 6.6676. Min Act: -0.1700
Data Index: 3966732 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4176. Min Range: -7.4176
Max Act: 6.6676. Min Act: -0.1700
Data Index: 5316882 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4176. Min Range: -7.4176
Max Act: 6.6676. Min Act: -0.1700
Data Index: 6872764 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19