Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3654 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1268. Min Range: -5.1268
Max Act: 5.0955. Min Act: -0.1700
Data Index: 2407212 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1268. Min Range: -5.1268
Max Act: 5.1268. Min Act: -0.1700
Data Index: 1598320 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1268. Min Range: -5.1268
Max Act: 5.0330. Min Act: -0.1700
Data Index: 3324506 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1268. Min Range: -5.1268
Max Act: 5.0018. Min Act: -0.1700
Data Index: 3902555 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1268. Min Range: -5.1268
Max Act: 5.0018. Min Act: -0.1700
Data Index: 8077004 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1268. Min Range: -5.1268
Max Act: 5.0018. Min Act: -0.1700
Data Index: 6116558 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1268. Min Range: -5.1268
Max Act: 4.9705. Min Act: -0.1700
Data Index: 2327220 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1268. Min Range: -5.1268
Max Act: 4.9705. Min Act: -0.1700
Data Index: 2439410 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1268. Min Range: -5.1268
Max Act: 4.9393. Min Act: -0.1700
Data Index: 4058507 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1268. Min Range: -5.1268
Max Act: 4.9393. Min Act: -0.1700
Data Index: 6263932 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1268. Min Range: -5.1268
Max Act: 4.9080. Min Act: -0.1700
Data Index: 4459576 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1268. Min Range: -5.1268
Max Act: 4.9393. Min Act: -0.1700
Data Index: 1086050 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1268. Min Range: -5.1268
Max Act: 4.9080. Min Act: -0.1700
Data Index: 3016842 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1268. Min Range: -5.1268
Max Act: 4.9080. Min Act: -0.1700
Data Index: 2312539 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1268. Min Range: -5.1268
Max Act: 4.9080. Min Act: -0.1700
Data Index: 2418851 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1268. Min Range: -5.1268
Max Act: 4.9080. Min Act: -0.1700
Data Index: 1297990 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1268. Min Range: -5.1268
Max Act: 4.9080. Min Act: -0.1700
Data Index: 638934 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1268. Min Range: -5.1268
Max Act: 4.8768. Min Act: -0.1700
Data Index: 6116560 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1268. Min Range: -5.1268
Max Act: 4.8768. Min Act: -0.1700
Data Index: 1598341 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1268. Min Range: -5.1268
Max Act: 4.8768. Min Act: -0.1700
Data Index: 1621874 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19