Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2016 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5602. Min Range: -4.5602
Max Act: 4.5602. Min Act: -0.1700
Data Index: 391936 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5602. Min Range: -4.5602
Max Act: 4.5602. Min Act: -0.1700
Data Index: 3025314 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5602. Min Range: -4.5602
Max Act: 4.5290. Min Act: -0.1700
Data Index: 1236932 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5602. Min Range: -4.5602
Max Act: 4.4665. Min Act: -0.1700
Data Index: 7828618 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5602. Min Range: -4.5602
Max Act: 4.4665. Min Act: -0.1700
Data Index: 277704 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5602. Min Range: -4.5602
Max Act: 4.4665. Min Act: -0.1700
Data Index: 253246 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5602. Min Range: -4.5602
Max Act: 4.4352. Min Act: -0.1700
Data Index: 1439338 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5602. Min Range: -4.5602
Max Act: 4.4352. Min Act: -0.1700
Data Index: 1033321 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5602. Min Range: -4.5602
Max Act: 4.4352. Min Act: -0.1700
Data Index: 3164966 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5602. Min Range: -4.5602
Max Act: 4.4352. Min Act: -0.1700
Data Index: 7168166 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5602. Min Range: -4.5602
Max Act: 4.4040. Min Act: -0.1700
Data Index: 7401796 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5602. Min Range: -4.5602
Max Act: 4.4040. Min Act: -0.1700
Data Index: 7715532 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5602. Min Range: -4.5602
Max Act: 4.3727. Min Act: -0.1700
Data Index: 6320951 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5602. Min Range: -4.5602
Max Act: 4.3727. Min Act: -0.1700
Data Index: 6375779 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5602. Min Range: -4.5602
Max Act: 4.3727. Min Act: -0.1700
Data Index: 6855177 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5602. Min Range: -4.5602
Max Act: 4.3727. Min Act: -0.1700
Data Index: 325679 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5602. Min Range: -4.5602
Max Act: 4.3727. Min Act: -0.1700
Data Index: 1617331 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5602. Min Range: -4.5602
Max Act: 4.4040. Min Act: -0.1700
Data Index: 6181673 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5602. Min Range: -4.5602
Max Act: 4.3415. Min Act: -0.1700
Data Index: 157150 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5602. Min Range: -4.5602
Max Act: 4.3415. Min Act: -0.1700
Data Index: 3011762 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19