Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1655 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0492. Min Range: -4.0492
Max Act: 4.0492. Min Act: -0.1700
Data Index: 8449713 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0492. Min Range: -4.0492
Max Act: 4.0179. Min Act: -0.1700
Data Index: 5039634 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0492. Min Range: -4.0492
Max Act: 4.0492. Min Act: -0.1700
Data Index: 3935641 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0492. Min Range: -4.0492
Max Act: 4.0179. Min Act: -0.1700
Data Index: 1719908 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0492. Min Range: -4.0492
Max Act: 4.0492. Min Act: -0.1700
Data Index: 5911981 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0492. Min Range: -4.0492
Max Act: 4.0179. Min Act: -0.1700
Data Index: 8566619 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0492. Min Range: -4.0492
Max Act: 4.0492. Min Act: -0.1700
Data Index: 4730806 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0492. Min Range: -4.0492
Max Act: 4.0179. Min Act: -0.1700
Data Index: 7428039 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.9554. Min Act: -0.1700
Data Index: 1639430 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.9554. Min Act: -0.1700
Data Index: 8370378 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.9554. Min Act: -0.1700
Data Index: 1719907 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.9241. Min Act: -0.1700
Data Index: 8566618 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.9241. Min Act: -0.1700
Data Index: 679771 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.8929. Min Act: -0.1700
Data Index: 3392039 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.8929. Min Act: -0.1700
Data Index: 5039633 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.8929. Min Act: -0.1700
Data Index: 8449712 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.8616. Min Act: -0.1700
Data Index: 7614158 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.8303. Min Act: -0.1700
Data Index: 7958064 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.7834. Min Act: -0.1700
Data Index: 5419614 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.7678. Min Act: -0.1700
Data Index: 6916999 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19