Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 26 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0453. Min Range: -7.0453
Max Act: 7.0453. Min Act: -0.1700
Data Index: 3194263 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0453. Min Range: -7.0453
Max Act: 7.0141. Min Act: -0.1700
Data Index: 8000947 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0453. Min Range: -7.0453
Max Act: 6.9828. Min Act: -0.1700
Data Index: 8316029 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0453. Min Range: -7.0453
Max Act: 6.9516. Min Act: -0.1700
Data Index: 6992636 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0453. Min Range: -7.0453
Max Act: 6.8266. Min Act: -0.1700
Data Index: 5615601 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0453. Min Range: -7.0453
Max Act: 6.8266. Min Act: -0.1700
Data Index: 5286598 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0453. Min Range: -7.0453
Max Act: 6.7641. Min Act: -0.1700
Data Index: 3147694 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0453. Min Range: -7.0453
Max Act: 6.7641. Min Act: -0.1700
Data Index: 7614419 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0453. Min Range: -7.0453
Max Act: 6.7328. Min Act: -0.1700
Data Index: 5881450 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0453. Min Range: -7.0453
Max Act: 6.7328. Min Act: -0.1700
Data Index: 2430181 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0453. Min Range: -7.0453
Max Act: 6.7328. Min Act: -0.1700
Data Index: 2901410 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0453. Min Range: -7.0453
Max Act: 6.6391. Min Act: -0.1700
Data Index: 6389273 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0453. Min Range: -7.0453
Max Act: 6.6391. Min Act: -0.1700
Data Index: 8133554 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0453. Min Range: -7.0453
Max Act: 6.6078. Min Act: -0.1700
Data Index: 6051666 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0453. Min Range: -7.0453
Max Act: 6.6078. Min Act: -0.1700
Data Index: 7733261 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0453. Min Range: -7.0453
Max Act: 6.6078. Min Act: -0.1700
Data Index: 4059230 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0453. Min Range: -7.0453
Max Act: 6.5766. Min Act: -0.1700
Data Index: 846948 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0453. Min Range: -7.0453
Max Act: 6.5766. Min Act: -0.1700
Data Index: 4405614 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0453. Min Range: -7.0453
Max Act: 6.5766. Min Act: -0.1700
Data Index: 3279495 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0453. Min Range: -7.0453
Max Act: 6.5766. Min Act: -0.1700
Data Index: 2571320 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19