Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3112 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.5428. Min Act: -0.1700
Data Index: 3941214 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.5428. Min Act: -0.1700
Data Index: 360065 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.5115. Min Act: -0.1700
Data Index: 7352204 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.5115. Min Act: -0.1700
Data Index: 1565764 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.5115. Min Act: -0.1700
Data Index: 8240722 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4178. Min Act: -0.1700
Data Index: 4549591 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4490. Min Act: -0.1700
Data Index: 5288207 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4178. Min Act: -0.1700
Data Index: 1976625 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4178. Min Act: -0.1700
Data Index: 5089564 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4178. Min Act: -0.1700
Data Index: 2436126 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4178. Min Act: -0.1700
Data Index: 1649331 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.3865. Min Act: -0.1700
Data Index: 8140722 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4178. Min Act: -0.1700
Data Index: 7218324 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.3865. Min Act: -0.1700
Data Index: 2852545 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.3553. Min Act: -0.1700
Data Index: 8267171 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.3553. Min Act: -0.1700
Data Index: 3126226 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.3240. Min Act: -0.1700
Data Index: 1739141 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.3240. Min Act: -0.1700
Data Index: 7493302 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.3240. Min Act: -0.1700
Data Index: 4561092 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.2928. Min Act: -0.1700
Data Index: 5728374 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19