Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1851 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3018. Min Range: -9.3018
Max Act: 9.3018. Min Act: -0.1700
Data Index: 578330 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3018. Min Range: -9.3018
Max Act: 9.1768. Min Act: -0.1700
Data Index: 4799605 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3018. Min Range: -9.3018
Max Act: 9.2393. Min Act: -0.1700
Data Index: 3731647 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3018. Min Range: -9.3018
Max Act: 9.1143. Min Act: -0.1700
Data Index: 5122043 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3018. Min Range: -9.3018
Max Act: 9.0518. Min Act: -0.1700
Data Index: 6371823 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3018. Min Range: -9.3018
Max Act: 8.9893. Min Act: -0.1700
Data Index: 5979904 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3018. Min Range: -9.3018
Max Act: 8.9893. Min Act: -0.1700
Data Index: 4218904 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3018. Min Range: -9.3018
Max Act: 8.9893. Min Act: -0.1700
Data Index: 8582539 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3018. Min Range: -9.3018
Max Act: 8.9268. Min Act: -0.1700
Data Index: 3733832 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3018. Min Range: -9.3018
Max Act: 8.9268. Min Act: -0.1700
Data Index: 1603790 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3018. Min Range: -9.3018
Max Act: 8.8643. Min Act: -0.1700
Data Index: 7463829 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3018. Min Range: -9.3018
Max Act: 8.8018. Min Act: -0.1700
Data Index: 6976809 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3018. Min Range: -9.3018
Max Act: 8.8018. Min Act: -0.1700
Data Index: 7377329 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3018. Min Range: -9.3018
Max Act: 8.8018. Min Act: -0.1700
Data Index: 6167433 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3018. Min Range: -9.3018
Max Act: 8.7393. Min Act: -0.1700
Data Index: 7299834 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3018. Min Range: -9.3018
Max Act: 8.7393. Min Act: -0.1700
Data Index: 4580658 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3018. Min Range: -9.3018
Max Act: 8.6768. Min Act: -0.1700
Data Index: 5498569 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3018. Min Range: -9.3018
Max Act: 8.6768. Min Act: -0.1700
Data Index: 3148106 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3018. Min Range: -9.3018
Max Act: 8.6768. Min Act: -0.1700
Data Index: 5736695 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3018. Min Range: -9.3018
Max Act: 8.6768. Min Act: -0.1700
Data Index: 3554811 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19