Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 426 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6174. Min Range: -10.6174
Max Act: 10.6174. Min Act: -0.1700
Data Index: 7949434 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6174. Min Range: -10.6174
Max Act: 10.6174. Min Act: -0.1700
Data Index: 7949455 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6174. Min Range: -10.6174
Max Act: 10.6174. Min Act: -0.1700
Data Index: 7318812 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6174. Min Range: -10.6174
Max Act: 10.6174. Min Act: -0.1700
Data Index: 923162 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6174. Min Range: -10.6174
Max Act: 10.5549. Min Act: -0.1700
Data Index: 2002792 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6174. Min Range: -10.6174
Max Act: 10.5549. Min Act: -0.1700
Data Index: 7949438 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6174. Min Range: -10.6174
Max Act: 10.5549. Min Act: -0.1676
Data Index: 5787264 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6174. Min Range: -10.6174
Max Act: 10.4924. Min Act: -0.1672
Data Index: 5787258 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6174. Min Range: -10.6174
Max Act: 10.4924. Min Act: -0.1700
Data Index: 4574834 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6174. Min Range: -10.6174
Max Act: 10.4924. Min Act: -0.1700
Data Index: 1561746 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6174. Min Range: -10.6174
Max Act: 10.4924. Min Act: -0.1274
Data Index: 5787281 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6174. Min Range: -10.6174
Max Act: 10.4924. Min Act: -0.1663
Data Index: 5787265 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6174. Min Range: -10.6174
Max Act: 10.4924. Min Act: -0.1588
Data Index: 5787247 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6174. Min Range: -10.6174
Max Act: 10.4299. Min Act: -0.1700
Data Index: 1261243 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6174. Min Range: -10.6174
Max Act: 10.4299. Min Act: -0.1700
Data Index: 2527783 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6174. Min Range: -10.6174
Max Act: 10.4299. Min Act: -0.1695
Data Index: 5787241 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6174. Min Range: -10.6174
Max Act: 10.4299. Min Act: -0.1606
Data Index: 5787257 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6174. Min Range: -10.6174
Max Act: 10.4299. Min Act: -0.1700
Data Index: 2938643 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6174. Min Range: -10.6174
Max Act: 10.4924. Min Act: -0.1700
Data Index: 1561761 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6174. Min Range: -10.6174
Max Act: 10.4299. Min Act: -0.1700
Data Index: 7393360 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19