Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4600 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0206. Min Range: -7.0206
Max Act: 7.0206. Min Act: -0.1700
Data Index: 1720769 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0206. Min Range: -7.0206
Max Act: 7.0206. Min Act: -0.1700
Data Index: 498559 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0206. Min Range: -7.0206
Max Act: 6.8956. Min Act: -0.1700
Data Index: 7439416 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0206. Min Range: -7.0206
Max Act: 6.8644. Min Act: -0.1700
Data Index: 7831529 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0206. Min Range: -7.0206
Max Act: 6.7706. Min Act: -0.1700
Data Index: 5121803 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0206. Min Range: -7.0206
Max Act: 6.7706. Min Act: -0.1700
Data Index: 5926236 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0206. Min Range: -7.0206
Max Act: 6.6769. Min Act: -0.1700
Data Index: 1521892 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0206. Min Range: -7.0206
Max Act: 6.7081. Min Act: -0.1700
Data Index: 2495593 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0206. Min Range: -7.0206
Max Act: 6.7081. Min Act: -0.1700
Data Index: 2601358 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0206. Min Range: -7.0206
Max Act: 6.7394. Min Act: -0.1700
Data Index: 502900 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0206. Min Range: -7.0206
Max Act: 6.6769. Min Act: -0.1700
Data Index: 1248279 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0206. Min Range: -7.0206
Max Act: 6.6769. Min Act: -0.1700
Data Index: 1466518 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0206. Min Range: -7.0206
Max Act: 6.6769. Min Act: -0.1700
Data Index: 4070449 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0206. Min Range: -7.0206
Max Act: 6.6769. Min Act: -0.1700
Data Index: 7827501 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0206. Min Range: -7.0206
Max Act: 6.6144. Min Act: -0.1700
Data Index: 2600893 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0206. Min Range: -7.0206
Max Act: 6.6144. Min Act: -0.1700
Data Index: 1471965 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0206. Min Range: -7.0206
Max Act: 6.5831. Min Act: -0.1700
Data Index: 3788081 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0206. Min Range: -7.0206
Max Act: 6.5831. Min Act: -0.1700
Data Index: 1829827 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0206. Min Range: -7.0206
Max Act: 6.5831. Min Act: -0.1700
Data Index: 2949931 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0206. Min Range: -7.0206
Max Act: 6.5519. Min Act: -0.1700
Data Index: 6507539 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19