Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1642 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6042. Min Range: -6.6042
Max Act: 6.6042. Min Act: -0.1700
Data Index: 6040638 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6042. Min Range: -6.6042
Max Act: 6.5729. Min Act: -0.1700
Data Index: 8251138 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6042. Min Range: -6.6042
Max Act: 6.6042. Min Act: -0.1700
Data Index: 4343921 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6042. Min Range: -6.6042
Max Act: 6.5417. Min Act: -0.1700
Data Index: 2502608 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6042. Min Range: -6.6042
Max Act: 6.4167. Min Act: -0.1700
Data Index: 8665202 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6042. Min Range: -6.6042
Max Act: 6.4167. Min Act: -0.1700
Data Index: 3603911 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6042. Min Range: -6.6042
Max Act: 6.3854. Min Act: -0.1700
Data Index: 5960108 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6042. Min Range: -6.6042
Max Act: 6.2917. Min Act: -0.1700
Data Index: 1558429 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6042. Min Range: -6.6042
Max Act: 6.2917. Min Act: -0.1700
Data Index: 333277 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6042. Min Range: -6.6042
Max Act: 6.2604. Min Act: -0.1700
Data Index: 2727003 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6042. Min Range: -6.6042
Max Act: 6.2292. Min Act: -0.1700
Data Index: 1259259 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6042. Min Range: -6.6042
Max Act: 6.2604. Min Act: -0.1700
Data Index: 7605974 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6042. Min Range: -6.6042
Max Act: 6.1979. Min Act: -0.1700
Data Index: 2077369 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6042. Min Range: -6.6042
Max Act: 6.1667. Min Act: -0.1700
Data Index: 3695555 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6042. Min Range: -6.6042
Max Act: 6.1667. Min Act: -0.1700
Data Index: 738337 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6042. Min Range: -6.6042
Max Act: 6.1042. Min Act: -0.1700
Data Index: 7690664 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6042. Min Range: -6.6042
Max Act: 6.1042. Min Act: -0.1700
Data Index: 8744666 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6042. Min Range: -6.6042
Max Act: 6.1042. Min Act: -0.1700
Data Index: 8568390 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6042. Min Range: -6.6042
Max Act: 6.1042. Min Act: -0.1700
Data Index: 1757478 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6042. Min Range: -6.6042
Max Act: 6.0417. Min Act: -0.1700
Data Index: 1557517 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19