Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3105 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3696. Min Range: -8.3696
Max Act: 8.3696. Min Act: -0.1700
Data Index: 2816807 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3696. Min Range: -8.3696
Max Act: 8.1196. Min Act: -0.1700
Data Index: 4603509 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3696. Min Range: -8.3696
Max Act: 8.0571. Min Act: -0.1700
Data Index: 322198 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3696. Min Range: -8.3696
Max Act: 8.0571. Min Act: -0.1700
Data Index: 5343443 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3696. Min Range: -8.3696
Max Act: 7.9946. Min Act: -0.1700
Data Index: 530821 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3696. Min Range: -8.3696
Max Act: 7.9009. Min Act: -0.1700
Data Index: 5502340 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3696. Min Range: -8.3696
Max Act: 7.8696. Min Act: -0.1700
Data Index: 2486557 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3696. Min Range: -8.3696
Max Act: 7.8384. Min Act: -0.1700
Data Index: 1972535 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3696. Min Range: -8.3696
Max Act: 7.8071. Min Act: -0.1700
Data Index: 3005206 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3696. Min Range: -8.3696
Max Act: 7.8071. Min Act: -0.1700
Data Index: 77115 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3696. Min Range: -8.3696
Max Act: 7.7446. Min Act: -0.1700
Data Index: 7623131 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3696. Min Range: -8.3696
Max Act: 7.7446. Min Act: -0.1700
Data Index: 985901 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3696. Min Range: -8.3696
Max Act: 7.7446. Min Act: -0.1700
Data Index: 4611528 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3696. Min Range: -8.3696
Max Act: 7.7134. Min Act: -0.1700
Data Index: 7037038 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3696. Min Range: -8.3696
Max Act: 7.7134. Min Act: -0.1700
Data Index: 4713068 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3696. Min Range: -8.3696
Max Act: 7.6821. Min Act: -0.1700
Data Index: 5099213 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3696. Min Range: -8.3696
Max Act: 7.6509. Min Act: -0.1700
Data Index: 937909 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3696. Min Range: -8.3696
Max Act: 7.6509. Min Act: -0.1700
Data Index: 7747475 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3696. Min Range: -8.3696
Max Act: 7.5571. Min Act: -0.1700
Data Index: 1039435 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3696. Min Range: -8.3696
Max Act: 7.5571. Min Act: -0.1700
Data Index: 3750247 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19