Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 737 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.5313. Min Act: -0.1700
Data Index: 2521579 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.5157. Min Act: -0.1700
Data Index: 5858571 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.4530. Min Act: -0.1700
Data Index: 5045231 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.4217. Min Act: -0.1700
Data Index: 5734164 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.3903. Min Act: -0.1700
Data Index: 4495578 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.3590. Min Act: -0.1700
Data Index: 7966238 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.3276. Min Act: -0.1700
Data Index: 6451887 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.3276. Min Act: -0.1700
Data Index: 917506 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.3276. Min Act: -0.1700
Data Index: 7440079 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.2962. Min Act: -0.1700
Data Index: 4108416 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.3119. Min Act: -0.1700
Data Index: 5541068 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.2962. Min Act: -0.1700
Data Index: 6366931 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.2648. Min Act: -0.1700
Data Index: 2966386 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.2962. Min Act: -0.1700
Data Index: 2256286 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.2805. Min Act: -0.1700
Data Index: 5895214 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.2648. Min Act: -0.1700
Data Index: 7526369 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.2648. Min Act: -0.1700
Data Index: 466054 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.2648. Min Act: -0.1700
Data Index: 2489840 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.2648. Min Act: -0.1700
Data Index: 6992765 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.2491. Min Act: -0.1700
Data Index: 1634486 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19