Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1025 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6476. Min Range: -1.6476
Max Act: 1.6476. Min Act: -0.1700
Data Index: 4615185 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6476. Min Range: -1.6476
Max Act: 1.6214. Min Act: -0.1700
Data Index: 4810483 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6476. Min Range: -1.6476
Max Act: 1.6040. Min Act: -0.1700
Data Index: 818564 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6476. Min Range: -1.6476
Max Act: 1.5165. Min Act: -0.1700
Data Index: 2427040 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6476. Min Range: -1.6476
Max Act: 1.5340. Min Act: -0.1700
Data Index: 3012069 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6476. Min Range: -1.6476
Max Act: 1.5428. Min Act: -0.1700
Data Index: 7127763 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6476. Min Range: -1.6476
Max Act: 1.4901. Min Act: -0.1700
Data Index: 3315054 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6476. Min Range: -1.6476
Max Act: 1.4989. Min Act: -0.1700
Data Index: 6001577 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6476. Min Range: -1.6476
Max Act: 1.4989. Min Act: -0.1700
Data Index: 3469200 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6476. Min Range: -1.6476
Max Act: 1.5252. Min Act: -0.1700
Data Index: 4842763 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6476. Min Range: -1.6476
Max Act: 1.5077. Min Act: -0.1700
Data Index: 1430301 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6476. Min Range: -1.6476
Max Act: 1.4989. Min Act: -0.1700
Data Index: 452337 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6476. Min Range: -1.6476
Max Act: 1.4813. Min Act: -0.1700
Data Index: 7486999 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6476. Min Range: -1.6476
Max Act: 1.5077. Min Act: -0.1700
Data Index: 8102673 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6476. Min Range: -1.6476
Max Act: 1.4638. Min Act: -0.1700
Data Index: 1157000 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6476. Min Range: -1.6476
Max Act: 1.4725. Min Act: -0.1700
Data Index: 2430388 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6476. Min Range: -1.6476
Max Act: 1.4901. Min Act: -0.1700
Data Index: 6093597 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6476. Min Range: -1.6476
Max Act: 1.4901. Min Act: -0.1700
Data Index: 5878293 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6476. Min Range: -1.6476
Max Act: 1.4901. Min Act: -0.1700
Data Index: 8378104 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6476. Min Range: -1.6476
Max Act: 1.4989. Min Act: -0.1700
Data Index: 7914633 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19