Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5467 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1596. Min Range: -7.1596
Max Act: 7.1596. Min Act: -0.1700
Data Index: 1277494 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1596. Min Range: -7.1596
Max Act: 6.9721. Min Act: -0.1700
Data Index: 6448280 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1596. Min Range: -7.1596
Max Act: 6.9409. Min Act: -0.1700
Data Index: 943287 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1596. Min Range: -7.1596
Max Act: 6.9721. Min Act: -0.1700
Data Index: 6081855 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1596. Min Range: -7.1596
Max Act: 6.9721. Min Act: -0.1700
Data Index: 804782 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1596. Min Range: -7.1596
Max Act: 6.8784. Min Act: -0.1700
Data Index: 8359931 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1596. Min Range: -7.1596
Max Act: 6.8471. Min Act: -0.1700
Data Index: 7488028 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1596. Min Range: -7.1596
Max Act: 6.8471. Min Act: -0.1700
Data Index: 3530482 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1596. Min Range: -7.1596
Max Act: 6.8471. Min Act: -0.1700
Data Index: 3075581 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1596. Min Range: -7.1596
Max Act: 6.8159. Min Act: -0.1700
Data Index: 601412 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1596. Min Range: -7.1596
Max Act: 6.8159. Min Act: -0.1700
Data Index: 7117107 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1596. Min Range: -7.1596
Max Act: 6.7846. Min Act: -0.1700
Data Index: 5789299 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1596. Min Range: -7.1596
Max Act: 6.8159. Min Act: -0.1700
Data Index: 218301 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1596. Min Range: -7.1596
Max Act: 6.7846. Min Act: -0.1700
Data Index: 4667766 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1596. Min Range: -7.1596
Max Act: 6.7534. Min Act: -0.1700
Data Index: 6895063 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1596. Min Range: -7.1596
Max Act: 6.7221. Min Act: -0.1700
Data Index: 8359930 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1596. Min Range: -7.1596
Max Act: 6.7534. Min Act: -0.1700
Data Index: 7958951 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1596. Min Range: -7.1596
Max Act: 6.7534. Min Act: -0.1700
Data Index: 2914919 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1596. Min Range: -7.1596
Max Act: 6.6909. Min Act: -0.1700
Data Index: 8824578 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1596. Min Range: -7.1596
Max Act: 6.6909. Min Act: -0.1700
Data Index: 2003732 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19