Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1918 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5637. Min Range: -4.5637
Max Act: 4.5637. Min Act: -0.1700
Data Index: 3324370 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5637. Min Range: -4.5637
Max Act: 4.5325. Min Act: -0.1700
Data Index: 7769645 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5637. Min Range: -4.5637
Max Act: 4.5325. Min Act: -0.1700
Data Index: 7271382 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5637. Min Range: -4.5637
Max Act: 4.5012. Min Act: -0.1700
Data Index: 5327129 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5637. Min Range: -4.5637
Max Act: 4.5012. Min Act: -0.1700
Data Index: 5875361 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5637. Min Range: -4.5637
Max Act: 4.5012. Min Act: -0.1700
Data Index: 2149733 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5637. Min Range: -4.5637
Max Act: 4.5012. Min Act: -0.1700
Data Index: 6610283 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5637. Min Range: -4.5637
Max Act: 4.4700. Min Act: -0.1700
Data Index: 4089612 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5637. Min Range: -4.5637
Max Act: 4.4700. Min Act: -0.1700
Data Index: 8505936 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5637. Min Range: -4.5637
Max Act: 4.4700. Min Act: -0.1700
Data Index: 7895501 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5637. Min Range: -4.5637
Max Act: 4.4700. Min Act: -0.1700
Data Index: 2481815 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5637. Min Range: -4.5637
Max Act: 4.4700. Min Act: -0.1700
Data Index: 5112701 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5637. Min Range: -4.5637
Max Act: 4.4700. Min Act: -0.1700
Data Index: 4931570 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5637. Min Range: -4.5637
Max Act: 4.4700. Min Act: -0.1700
Data Index: 4924553 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5637. Min Range: -4.5637
Max Act: 4.4700. Min Act: -0.1700
Data Index: 4748114 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5637. Min Range: -4.5637
Max Act: 4.4074. Min Act: -0.1700
Data Index: 2758130 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5637. Min Range: -4.5637
Max Act: 4.4387. Min Act: -0.1700
Data Index: 1493689 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5637. Min Range: -4.5637
Max Act: 4.4387. Min Act: -0.1700
Data Index: 456104 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5637. Min Range: -4.5637
Max Act: 4.4387. Min Act: -0.1700
Data Index: 797445 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5637. Min Range: -4.5637
Max Act: 4.4387. Min Act: -0.1700
Data Index: 1637855 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19