Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1772 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.4977. Min Act: -0.1700
Data Index: 6148277 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.4664. Min Act: -0.1700
Data Index: 577278 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.4352. Min Act: -0.1700
Data Index: 4302472 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.4039. Min Act: -0.1700
Data Index: 5497057 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.4039. Min Act: -0.1700
Data Index: 4164783 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.3414. Min Act: -0.1700
Data Index: 3762635 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.3102. Min Act: -0.1700
Data Index: 511222 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.3102. Min Act: -0.1700
Data Index: 5740904 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.3414. Min Act: -0.1700
Data Index: 8557010 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.3102. Min Act: -0.1700
Data Index: 4226169 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.3102. Min Act: -0.1700
Data Index: 3814942 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2789. Min Act: -0.1700
Data Index: 6765206 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2789. Min Act: -0.1700
Data Index: 1013781 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2789. Min Act: -0.1700
Data Index: 952100 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2789. Min Act: -0.1700
Data Index: 4223420 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2789. Min Act: -0.1700
Data Index: 7399300 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2789. Min Act: -0.1700
Data Index: 5101579 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2477. Min Act: -0.1700
Data Index: 675233 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2789. Min Act: -0.1700
Data Index: 5045947 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2789. Min Act: -0.1700
Data Index: 3789395 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19