Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 53 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0420. Min Range: -4.0420
Max Act: 4.0420. Min Act: -0.1700
Data Index: 491016 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0420. Min Range: -4.0420
Max Act: 3.8544. Min Act: -0.1700
Data Index: 861248 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0420. Min Range: -4.0420
Max Act: 3.8544. Min Act: -0.1700
Data Index: 5509150 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0420. Min Range: -4.0420
Max Act: 3.8232. Min Act: -0.1700
Data Index: 8459197 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0420. Min Range: -4.0420
Max Act: 3.7762. Min Act: -0.1700
Data Index: 6207450 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0420. Min Range: -4.0420
Max Act: 3.7137. Min Act: -0.1700
Data Index: 2291660 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0420. Min Range: -4.0420
Max Act: 3.6980. Min Act: -0.1700
Data Index: 6077142 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0420. Min Range: -4.0420
Max Act: 3.6824. Min Act: -0.1700
Data Index: 3273910 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0420. Min Range: -4.0420
Max Act: 3.6980. Min Act: -0.1700
Data Index: 4759188 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0420. Min Range: -4.0420
Max Act: 3.6668. Min Act: -0.1700
Data Index: 4223378 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0420. Min Range: -4.0420
Max Act: 3.6668. Min Act: -0.1700
Data Index: 7892910 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0420. Min Range: -4.0420
Max Act: 3.6668. Min Act: -0.1700
Data Index: 2881839 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0420. Min Range: -4.0420
Max Act: 3.6511. Min Act: -0.1700
Data Index: 6266685 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0420. Min Range: -4.0420
Max Act: 3.6511. Min Act: -0.1700
Data Index: 1291885 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0420. Min Range: -4.0420
Max Act: 3.6511. Min Act: -0.1700
Data Index: 4263007 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0420. Min Range: -4.0420
Max Act: 3.6355. Min Act: -0.1700
Data Index: 8654202 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0420. Min Range: -4.0420
Max Act: 3.6355. Min Act: -0.1700
Data Index: 3466294 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0420. Min Range: -4.0420
Max Act: 3.6355. Min Act: -0.1700
Data Index: 2295981 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0420. Min Range: -4.0420
Max Act: 3.6355. Min Act: -0.1700
Data Index: 6190238 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0420. Min Range: -4.0420
Max Act: 3.6355. Min Act: -0.1700
Data Index: 5177854 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19