Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 49 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5691. Min Range: -3.5691
Max Act: 3.5691. Min Act: -0.1700
Data Index: 8291119 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5691. Min Range: -3.5691
Max Act: 3.4125. Min Act: -0.1700
Data Index: 2269532 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5691. Min Range: -3.5691
Max Act: 3.3498. Min Act: -0.1700
Data Index: 7243653 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5691. Min Range: -3.5691
Max Act: 3.3654. Min Act: -0.1700
Data Index: 1834001 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5691. Min Range: -3.5691
Max Act: 3.3341. Min Act: -0.1700
Data Index: 5273046 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5691. Min Range: -3.5691
Max Act: 3.3027. Min Act: -0.1700
Data Index: 7281126 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5691. Min Range: -3.5691
Max Act: 3.3341. Min Act: -0.1700
Data Index: 1032028 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5691. Min Range: -3.5691
Max Act: 3.2870. Min Act: -0.1700
Data Index: 3677872 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5691. Min Range: -3.5691
Max Act: 3.3184. Min Act: -0.1700
Data Index: 7670753 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5691. Min Range: -3.5691
Max Act: 3.2870. Min Act: -0.1700
Data Index: 325963 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5691. Min Range: -3.5691
Max Act: 3.2870. Min Act: -0.1700
Data Index: 3936565 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5691. Min Range: -3.5691
Max Act: 3.2713. Min Act: -0.1700
Data Index: 6063188 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5691. Min Range: -3.5691
Max Act: 3.2870. Min Act: -0.1700
Data Index: 4282765 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5691. Min Range: -3.5691
Max Act: 3.2713. Min Act: -0.1700
Data Index: 7451122 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5691. Min Range: -3.5691
Max Act: 3.2556. Min Act: -0.1700
Data Index: 848055 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5691. Min Range: -3.5691
Max Act: 3.2713. Min Act: -0.1700
Data Index: 4864673 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5691. Min Range: -3.5691
Max Act: 3.2713. Min Act: -0.1700
Data Index: 7281125 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5691. Min Range: -3.5691
Max Act: 3.2556. Min Act: -0.1700
Data Index: 5794427 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5691. Min Range: -3.5691
Max Act: 3.2399. Min Act: -0.1700
Data Index: 2810661 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5691. Min Range: -3.5691
Max Act: 3.2399. Min Act: -0.1700
Data Index: 2656559 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19