Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4780 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9162. Min Range: -4.9162
Max Act: 4.9162. Min Act: -0.1324
Data Index: 8787846 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9162. Min Range: -4.9162
Max Act: 4.9162. Min Act: -0.1089
Data Index: 2136139 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9162. Min Range: -4.9162
Max Act: 4.8225. Min Act: -0.1697
Data Index: 4383100 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9162. Min Range: -4.9162
Max Act: 4.8225. Min Act: -0.1617
Data Index: 190592 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9162. Min Range: -4.9162
Max Act: 4.7912. Min Act: -0.1440
Data Index: 2528145 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9162. Min Range: -4.9162
Max Act: 4.7600. Min Act: -0.1700
Data Index: 7610931 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9162. Min Range: -4.9162
Max Act: 4.7600. Min Act: -0.1690
Data Index: 3684140 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9162. Min Range: -4.9162
Max Act: 4.7287. Min Act: -0.1700
Data Index: 4008097 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9162. Min Range: -4.9162
Max Act: 4.7287. Min Act: -0.1690
Data Index: 7409335 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9162. Min Range: -4.9162
Max Act: 4.7287. Min Act: -0.1686
Data Index: 6972121 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9162. Min Range: -4.9162
Max Act: 4.7600. Min Act: -0.1700
Data Index: 1543013 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9162. Min Range: -4.9162
Max Act: 4.7287. Min Act: -0.1694
Data Index: 974168 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9162. Min Range: -4.9162
Max Act: 4.7287. Min Act: -0.1673
Data Index: 7801473 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9162. Min Range: -4.9162
Max Act: 4.7287. Min Act: -0.1700
Data Index: 4796722 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9162. Min Range: -4.9162
Max Act: 4.7287. Min Act: -0.1305
Data Index: 5010570 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9162. Min Range: -4.9162
Max Act: 4.6662. Min Act: -0.1700
Data Index: 7707504 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9162. Min Range: -4.9162
Max Act: 4.6662. Min Act: -0.1696
Data Index: 7888600 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9162. Min Range: -4.9162
Max Act: 4.6975. Min Act: -0.1394
Data Index: 8200128 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9162. Min Range: -4.9162
Max Act: 4.6975. Min Act: -0.1700
Data Index: 974979 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9162. Min Range: -4.9162
Max Act: 4.6975. Min Act: -0.1695
Data Index: 8570699 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19