Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2061 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2449. Min Range: -8.2449
Max Act: 8.2449. Min Act: -0.1700
Data Index: 3613024 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2449. Min Range: -8.2449
Max Act: 8.1199. Min Act: -0.1700
Data Index: 970461 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2449. Min Range: -8.2449
Max Act: 8.0574. Min Act: -0.1700
Data Index: 7157761 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2449. Min Range: -8.2449
Max Act: 8.0574. Min Act: -0.1700
Data Index: 7671017 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2449. Min Range: -8.2449
Max Act: 7.9324. Min Act: -0.1700
Data Index: 7115931 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2449. Min Range: -8.2449
Max Act: 7.8699. Min Act: -0.1700
Data Index: 4890254 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2449. Min Range: -8.2449
Max Act: 7.8699. Min Act: -0.1700
Data Index: 4425180 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2449. Min Range: -8.2449
Max Act: 7.8074. Min Act: -0.1700
Data Index: 5686708 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2449. Min Range: -8.2449
Max Act: 7.7449. Min Act: -0.1700
Data Index: 4432842 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2449. Min Range: -8.2449
Max Act: 7.7449. Min Act: -0.1700
Data Index: 2105213 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2449. Min Range: -8.2449
Max Act: 7.7449. Min Act: -0.1700
Data Index: 3862828 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2449. Min Range: -8.2449
Max Act: 7.7449. Min Act: -0.1700
Data Index: 1518220 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2449. Min Range: -8.2449
Max Act: 7.6824. Min Act: -0.1700
Data Index: 495039 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2449. Min Range: -8.2449
Max Act: 7.6824. Min Act: -0.1700
Data Index: 764273 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2449. Min Range: -8.2449
Max Act: 7.6824. Min Act: -0.1700
Data Index: 514704 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2449. Min Range: -8.2449
Max Act: 7.6824. Min Act: -0.1700
Data Index: 1364182 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2449. Min Range: -8.2449
Max Act: 7.6199. Min Act: -0.1700
Data Index: 2140586 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2449. Min Range: -8.2449
Max Act: 7.6199. Min Act: -0.1700
Data Index: 5198705 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2449. Min Range: -8.2449
Max Act: 7.6199. Min Act: -0.1700
Data Index: 494288 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2449. Min Range: -8.2449
Max Act: 7.6199. Min Act: -0.1700
Data Index: 2515802 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19