Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 547 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0532. Min Range: -3.0532
Max Act: 3.0532. Min Act: -0.1700
Data Index: 1152531 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0532. Min Range: -3.0532
Max Act: 3.0216. Min Act: -0.1700
Data Index: 3775355 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9900. Min Act: -0.1700
Data Index: 3194716 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9900. Min Act: -0.1700
Data Index: 2118429 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9742. Min Act: -0.1700
Data Index: 4083831 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9584. Min Act: -0.1700
Data Index: 6344743 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9584. Min Act: -0.1700
Data Index: 4569853 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9426. Min Act: -0.1700
Data Index: 3308612 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9426. Min Act: -0.1700
Data Index: 7876926 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9267. Min Act: -0.1700
Data Index: 7305758 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8950. Min Act: -0.1700
Data Index: 4205099 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9109. Min Act: -0.1700
Data Index: 8660024 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8950. Min Act: -0.1700
Data Index: 6754782 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8950. Min Act: -0.1700
Data Index: 4319226 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8950. Min Act: -0.1700
Data Index: 5361811 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8633. Min Act: -0.1700
Data Index: 2617354 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8633. Min Act: -0.1700
Data Index: 4399307 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8474. Min Act: -0.1700
Data Index: 6035799 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8474. Min Act: -0.1700
Data Index: 6209171 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8474. Min Act: -0.1700
Data Index: 3222546 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19