Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4436 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.2322. Min Act: -0.1700
Data Index: 2219434 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.2322. Min Act: -0.1700
Data Index: 564907 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.1536. Min Act: -0.1700
Data Index: 211187 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.1536. Min Act: -0.1700
Data Index: 327298 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.1378. Min Act: -0.1700
Data Index: 7444798 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.1378. Min Act: -0.1700
Data Index: 3876677 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.1221. Min Act: -0.1700
Data Index: 4088543 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.1221. Min Act: -0.1700
Data Index: 7690459 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.1063. Min Act: -0.1700
Data Index: 7806706 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.1063. Min Act: -0.1700
Data Index: 3549011 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.0906. Min Act: -0.1700
Data Index: 4944123 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.0906. Min Act: -0.1700
Data Index: 4115261 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.0906. Min Act: -0.1700
Data Index: 6217223 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.0906. Min Act: -0.1700
Data Index: 5766222 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.0748. Min Act: -0.1700
Data Index: 6217221 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.0748. Min Act: -0.1700
Data Index: 4821348 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.0748. Min Act: -0.1700
Data Index: 8121387 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.0590. Min Act: -0.1700
Data Index: 4463140 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.0748. Min Act: -0.1700
Data Index: 1173799 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.0590. Min Act: -0.1700
Data Index: 8028808 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19