Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3242 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6823. Min Range: -6.6823
Max Act: 6.6823. Min Act: -0.1700
Data Index: 7116317 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6823. Min Range: -6.6823
Max Act: 6.4323. Min Act: -0.1700
Data Index: 7657179 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6823. Min Range: -6.6823
Max Act: 6.3073. Min Act: -0.1700
Data Index: 5940050 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6823. Min Range: -6.6823
Max Act: 6.2448. Min Act: -0.1700
Data Index: 2686978 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6823. Min Range: -6.6823
Max Act: 6.1510. Min Act: -0.1700
Data Index: 804296 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6823. Min Range: -6.6823
Max Act: 6.0885. Min Act: -0.1700
Data Index: 4781624 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6823. Min Range: -6.6823
Max Act: 6.0885. Min Act: -0.1700
Data Index: 4533902 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6823. Min Range: -6.6823
Max Act: 6.0260. Min Act: -0.1700
Data Index: 5910974 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6823. Min Range: -6.6823
Max Act: 6.0260. Min Act: -0.1700
Data Index: 6989867 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6823. Min Range: -6.6823
Max Act: 6.0260. Min Act: -0.1700
Data Index: 2490379 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6823. Min Range: -6.6823
Max Act: 5.9635. Min Act: -0.1700
Data Index: 3984487 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6823. Min Range: -6.6823
Max Act: 5.9635. Min Act: -0.1700
Data Index: 7661601 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6823. Min Range: -6.6823
Max Act: 5.9323. Min Act: -0.1700
Data Index: 2104369 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6823. Min Range: -6.6823
Max Act: 5.9010. Min Act: -0.1700
Data Index: 637388 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6823. Min Range: -6.6823
Max Act: 5.8385. Min Act: -0.1700
Data Index: 6961615 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6823. Min Range: -6.6823
Max Act: 5.8698. Min Act: -0.1700
Data Index: 3870651 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6823. Min Range: -6.6823
Max Act: 5.8698. Min Act: -0.1700
Data Index: 2301582 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6823. Min Range: -6.6823
Max Act: 5.8698. Min Act: -0.1700
Data Index: 4254934 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6823. Min Range: -6.6823
Max Act: 5.8385. Min Act: -0.1700
Data Index: 7606457 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6823. Min Range: -6.6823
Max Act: 5.8385. Min Act: -0.1700
Data Index: 8323084 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19