Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 398 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5314. Min Range: -5.5314
Max Act: 5.5314. Min Act: -0.1700
Data Index: 930252 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5314. Min Range: -5.5314
Max Act: 5.4689. Min Act: -0.1700
Data Index: 7857236 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5314. Min Range: -5.5314
Max Act: 5.3127. Min Act: -0.1700
Data Index: 5342535 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5314. Min Range: -5.5314
Max Act: 5.2502. Min Act: -0.1700
Data Index: 5998854 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5314. Min Range: -5.5314
Max Act: 5.2502. Min Act: -0.1700
Data Index: 6174181 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5314. Min Range: -5.5314
Max Act: 5.3127. Min Act: -0.1700
Data Index: 6234557 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5314. Min Range: -5.5314
Max Act: 5.2502. Min Act: -0.1700
Data Index: 1995889 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5314. Min Range: -5.5314
Max Act: 5.2814. Min Act: -0.1700
Data Index: 3888201 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5314. Min Range: -5.5314
Max Act: 5.1877. Min Act: -0.1700
Data Index: 2378849 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5314. Min Range: -5.5314
Max Act: 5.0939. Min Act: -0.1700
Data Index: 5342536 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5314. Min Range: -5.5314
Max Act: 5.0939. Min Act: -0.1700
Data Index: 553525 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5314. Min Range: -5.5314
Max Act: 5.0627. Min Act: -0.1700
Data Index: 2544590 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5314. Min Range: -5.5314
Max Act: 5.0939. Min Act: -0.1700
Data Index: 775090 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5314. Min Range: -5.5314
Max Act: 5.0627. Min Act: -0.1700
Data Index: 2658441 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5314. Min Range: -5.5314
Max Act: 5.0002. Min Act: -0.1700
Data Index: 4041913 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5314. Min Range: -5.5314
Max Act: 5.0002. Min Act: -0.1700
Data Index: 1712645 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5314. Min Range: -5.5314
Max Act: 4.9689. Min Act: -0.1700
Data Index: 2733410 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5314. Min Range: -5.5314
Max Act: 4.9689. Min Act: -0.1700
Data Index: 2399886 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5314. Min Range: -5.5314
Max Act: 4.9689. Min Act: -0.1700
Data Index: 6537757 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5314. Min Range: -5.5314
Max Act: 4.9377. Min Act: -0.1700
Data Index: 2217642 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19