Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2266 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7276. Min Range: -4.7276
Max Act: 4.7276. Min Act: -0.1700
Data Index: 394128 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7276. Min Range: -4.7276
Max Act: 4.6963. Min Act: -0.1700
Data Index: 84040 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7276. Min Range: -4.7276
Max Act: 4.6963. Min Act: -0.1700
Data Index: 5449091 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7276. Min Range: -4.7276
Max Act: 4.6338. Min Act: -0.1700
Data Index: 5334733 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7276. Min Range: -4.7276
Max Act: 4.6338. Min Act: -0.1700
Data Index: 450000 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7276. Min Range: -4.7276
Max Act: 4.6338. Min Act: -0.1700
Data Index: 5757480 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7276. Min Range: -4.7276
Max Act: 4.6338. Min Act: -0.1700
Data Index: 6236711 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7276. Min Range: -4.7276
Max Act: 4.6026. Min Act: -0.1700
Data Index: 3107741 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7276. Min Range: -4.7276
Max Act: 4.6026. Min Act: -0.1700
Data Index: 2061097 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7276. Min Range: -4.7276
Max Act: 4.5401. Min Act: -0.1700
Data Index: 7870057 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7276. Min Range: -4.7276
Max Act: 4.5401. Min Act: -0.1700
Data Index: 960393 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7276. Min Range: -4.7276
Max Act: 4.5088. Min Act: -0.1700
Data Index: 5929526 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7276. Min Range: -4.7276
Max Act: 4.5088. Min Act: -0.1700
Data Index: 7336274 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7276. Min Range: -4.7276
Max Act: 4.4776. Min Act: -0.1700
Data Index: 1832101 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7276. Min Range: -4.7276
Max Act: 4.4463. Min Act: -0.1700
Data Index: 5450420 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7276. Min Range: -4.7276
Max Act: 4.4463. Min Act: -0.1700
Data Index: 8099298 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7276. Min Range: -4.7276
Max Act: 4.4463. Min Act: -0.1700
Data Index: 4599561 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7276. Min Range: -4.7276
Max Act: 4.4151. Min Act: -0.1700
Data Index: 4855795 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7276. Min Range: -4.7276
Max Act: 4.4151. Min Act: -0.1700
Data Index: 4766523 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7276. Min Range: -4.7276
Max Act: 4.4151. Min Act: -0.1700
Data Index: 1753645 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19