Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4347 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.3737. Min Act: -0.1700
Data Index: 6985944 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.4049. Min Act: -0.1700
Data Index: 4885911 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.3424. Min Act: -0.1700
Data Index: 2975060 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.3112. Min Act: -0.1700
Data Index: 3268012 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.3112. Min Act: -0.1700
Data Index: 2356269 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.2799. Min Act: -0.1700
Data Index: 3795739 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.2487. Min Act: -0.1700
Data Index: 2402019 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.2487. Min Act: -0.1700
Data Index: 2702514 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.2174. Min Act: -0.1700
Data Index: 3585687 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.2174. Min Act: -0.1700
Data Index: 741154 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.2487. Min Act: -0.1700
Data Index: 3629276 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.1862. Min Act: -0.1700
Data Index: 4859559 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.1862. Min Act: -0.1700
Data Index: 1234653 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.1862. Min Act: -0.1700
Data Index: 5145177 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.1862. Min Act: -0.1700
Data Index: 3763503 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.1549. Min Act: -0.1700
Data Index: 243379 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.1549. Min Act: -0.1700
Data Index: 2863543 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.1862. Min Act: -0.1700
Data Index: 6429008 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.1237. Min Act: -0.1700
Data Index: 1723402 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.1237. Min Act: -0.1700
Data Index: 2597399 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19