Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1614 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0185. Min Range: -4.0185
Max Act: 4.0185. Min Act: -0.1700
Data Index: 6328522 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0185. Min Range: -4.0185
Max Act: 3.9559. Min Act: -0.1700
Data Index: 4535759 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0185. Min Range: -4.0185
Max Act: 3.9090. Min Act: -0.1700
Data Index: 5831284 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0185. Min Range: -4.0185
Max Act: 3.9090. Min Act: -0.1700
Data Index: 2422689 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0185. Min Range: -4.0185
Max Act: 3.8621. Min Act: -0.1700
Data Index: 3976990 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0185. Min Range: -4.0185
Max Act: 3.8621. Min Act: -0.1700
Data Index: 5140308 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0185. Min Range: -4.0185
Max Act: 3.8778. Min Act: -0.1700
Data Index: 3805250 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0185. Min Range: -4.0185
Max Act: 3.8934. Min Act: -0.1700
Data Index: 6324463 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0185. Min Range: -4.0185
Max Act: 3.8778. Min Act: -0.1700
Data Index: 3514716 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0185. Min Range: -4.0185
Max Act: 3.8778. Min Act: -0.1700
Data Index: 7716791 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0185. Min Range: -4.0185
Max Act: 3.8465. Min Act: -0.1700
Data Index: 7308409 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0185. Min Range: -4.0185
Max Act: 3.8621. Min Act: -0.1700
Data Index: 1262488 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0185. Min Range: -4.0185
Max Act: 3.8465. Min Act: -0.1700
Data Index: 3976985 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0185. Min Range: -4.0185
Max Act: 3.8621. Min Act: -0.1700
Data Index: 4778654 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0185. Min Range: -4.0185
Max Act: 3.8152. Min Act: -0.1700
Data Index: 2968960 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0185. Min Range: -4.0185
Max Act: 3.8309. Min Act: -0.1700
Data Index: 1066980 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0185. Min Range: -4.0185
Max Act: 3.8152. Min Act: -0.1700
Data Index: 3396171 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0185. Min Range: -4.0185
Max Act: 3.7996. Min Act: -0.1700
Data Index: 5503687 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0185. Min Range: -4.0185
Max Act: 3.7840. Min Act: -0.1700
Data Index: 3976982 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0185. Min Range: -4.0185
Max Act: 3.8152. Min Act: -0.1700
Data Index: 1212124 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19