Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3417 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2769. Min Range: -4.2769
Max Act: 4.2769. Min Act: -0.1700
Data Index: 221242 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2769. Min Range: -4.2769
Max Act: 4.0268. Min Act: -0.1700
Data Index: 46957 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2769. Min Range: -4.2769
Max Act: 3.9956. Min Act: -0.1700
Data Index: 2574201 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2769. Min Range: -4.2769
Max Act: 3.9956. Min Act: -0.1700
Data Index: 1316609 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2769. Min Range: -4.2769
Max Act: 3.9330. Min Act: -0.1700
Data Index: 7229152 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2769. Min Range: -4.2769
Max Act: 3.9643. Min Act: -0.1700
Data Index: 789986 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2769. Min Range: -4.2769
Max Act: 3.9643. Min Act: -0.1700
Data Index: 2264239 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2769. Min Range: -4.2769
Max Act: 3.9643. Min Act: -0.1700
Data Index: 6039135 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2769. Min Range: -4.2769
Max Act: 3.9330. Min Act: -0.1700
Data Index: 4323001 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2769. Min Range: -4.2769
Max Act: 3.9330. Min Act: -0.1700
Data Index: 2996779 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2769. Min Range: -4.2769
Max Act: 3.9330. Min Act: -0.1700
Data Index: 1547470 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2769. Min Range: -4.2769
Max Act: 3.9018. Min Act: -0.1700
Data Index: 4473806 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2769. Min Range: -4.2769
Max Act: 3.9330. Min Act: -0.1700
Data Index: 4657362 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2769. Min Range: -4.2769
Max Act: 3.9018. Min Act: -0.1700
Data Index: 7170453 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2769. Min Range: -4.2769
Max Act: 3.9018. Min Act: -0.1700
Data Index: 8566993 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2769. Min Range: -4.2769
Max Act: 3.8705. Min Act: -0.1700
Data Index: 2004665 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2769. Min Range: -4.2769
Max Act: 3.9018. Min Act: -0.1700
Data Index: 1650891 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2769. Min Range: -4.2769
Max Act: 3.8862. Min Act: -0.1700
Data Index: 1811329 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2769. Min Range: -4.2769
Max Act: 3.8862. Min Act: -0.1700
Data Index: 2402605 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2769. Min Range: -4.2769
Max Act: 3.8705. Min Act: -0.1700
Data Index: 5259372 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19