Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4064 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.9100. Min Act: -0.1700
Data Index: 3649081 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.7538. Min Act: -0.1700
Data Index: 6199263 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.7850. Min Act: -0.1700
Data Index: 8679029 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.8163. Min Act: -0.1700
Data Index: 1436448 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.7850. Min Act: -0.1700
Data Index: 8105143 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.8163. Min Act: -0.1700
Data Index: 6932428 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.7538. Min Act: -0.1700
Data Index: 2760669 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.6913. Min Act: -0.1700
Data Index: 4987115 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.6913. Min Act: -0.1700
Data Index: 4706420 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.6600. Min Act: -0.1700
Data Index: 673485 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.6288. Min Act: -0.1700
Data Index: 6902824 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.6288. Min Act: -0.1700
Data Index: 2999128 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.6288. Min Act: -0.1700
Data Index: 2069957 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.6288. Min Act: -0.1700
Data Index: 8599943 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.5663. Min Act: -0.1700
Data Index: 4020480 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.6288. Min Act: -0.1700
Data Index: 3329270 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.6288. Min Act: -0.1700
Data Index: 6726000 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.6288. Min Act: -0.1700
Data Index: 7989713 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.5663. Min Act: -0.1700
Data Index: 761672 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.5975. Min Act: -0.1700
Data Index: 5817808 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19