Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 546 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5989. Min Range: -8.5989
Max Act: 8.5989. Min Act: -0.1700
Data Index: 2076373 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5989. Min Range: -8.5989
Max Act: 8.0677. Min Act: -0.1700
Data Index: 1208670 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5989. Min Range: -8.5989
Max Act: 7.7552. Min Act: -0.1700
Data Index: 520508 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5989. Min Range: -8.5989
Max Act: 7.6302. Min Act: -0.1700
Data Index: 6003133 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5989. Min Range: -8.5989
Max Act: 7.6302. Min Act: -0.1700
Data Index: 8639943 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5989. Min Range: -8.5989
Max Act: 7.5052. Min Act: -0.1700
Data Index: 1135307 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5989. Min Range: -8.5989
Max Act: 7.4427. Min Act: -0.1700
Data Index: 7486049 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5989. Min Range: -8.5989
Max Act: 7.4739. Min Act: -0.1700
Data Index: 2453232 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5989. Min Range: -8.5989
Max Act: 7.3802. Min Act: -0.1700
Data Index: 3073603 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5989. Min Range: -8.5989
Max Act: 7.4427. Min Act: -0.1700
Data Index: 4514480 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5989. Min Range: -8.5989
Max Act: 7.3802. Min Act: -0.1700
Data Index: 172112 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5989. Min Range: -8.5989
Max Act: 7.4114. Min Act: -0.1700
Data Index: 71722 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5989. Min Range: -8.5989
Max Act: 7.3489. Min Act: -0.1700
Data Index: 6465177 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5989. Min Range: -8.5989
Max Act: 7.2864. Min Act: -0.1700
Data Index: 7489866 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5989. Min Range: -8.5989
Max Act: 7.2552. Min Act: -0.1700
Data Index: 6002909 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5989. Min Range: -8.5989
Max Act: 7.2239. Min Act: -0.1700
Data Index: 6858293 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5989. Min Range: -8.5989
Max Act: 7.2239. Min Act: -0.1700
Data Index: 6649394 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5989. Min Range: -8.5989
Max Act: 7.2239. Min Act: -0.1700
Data Index: 1403278 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5989. Min Range: -8.5989
Max Act: 7.1927. Min Act: -0.1700
Data Index: 2525285 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5989. Min Range: -8.5989
Max Act: 7.1927. Min Act: -0.1700
Data Index: 3643617 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19