Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 794 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.7369. Min Act: -0.1700
Data Index: 5454396 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.7049. Min Act: -0.1700
Data Index: 2459215 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.7049. Min Act: -0.1700
Data Index: 6469028 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.7049. Min Act: -0.1700
Data Index: 1213501 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.7049. Min Act: -0.1700
Data Index: 8776549 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6729. Min Act: -0.1700
Data Index: 8427063 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6889. Min Act: -0.1700
Data Index: 61680 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6889. Min Act: -0.1700
Data Index: 6864236 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6729. Min Act: -0.1700
Data Index: 2112202 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6889. Min Act: -0.1700
Data Index: 4817991 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6729. Min Act: -0.1700
Data Index: 1300392 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6889. Min Act: -0.1700
Data Index: 6259830 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6568. Min Act: -0.1700
Data Index: 7794254 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6568. Min Act: -0.1700
Data Index: 3600881 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6568. Min Act: -0.1700
Data Index: 4738142 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6568. Min Act: -0.1700
Data Index: 509925 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6729. Min Act: -0.1700
Data Index: 8461452 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6408. Min Act: -0.1700
Data Index: 8419488 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6247. Min Act: -0.1700
Data Index: 2655053 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6408. Min Act: -0.1700
Data Index: 1745451 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19