Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1746 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2244. Min Range: -10.2244
Max Act: 10.2244. Min Act: -0.1699
Data Index: 6569326 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2244. Min Range: -10.2244
Max Act: 9.9744. Min Act: -0.1700
Data Index: 6569304 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2244. Min Range: -10.2244
Max Act: 9.6619. Min Act: -0.1700
Data Index: 3798338 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2244. Min Range: -10.2244
Max Act: 9.5994. Min Act: -0.1700
Data Index: 8767845 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2244. Min Range: -10.2244
Max Act: 9.4744. Min Act: -0.1700
Data Index: 3798337 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2244. Min Range: -10.2244
Max Act: 9.3494. Min Act: -0.1700
Data Index: 654424 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2244. Min Range: -10.2244
Max Act: 9.2869. Min Act: -0.1700
Data Index: 8561684 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2244. Min Range: -10.2244
Max Act: 9.2869. Min Act: -0.1700
Data Index: 453047 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2244. Min Range: -10.2244
Max Act: 9.2869. Min Act: -0.1700
Data Index: 3120423 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2244. Min Range: -10.2244
Max Act: 9.2869. Min Act: -0.1700
Data Index: 8536122 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2244. Min Range: -10.2244
Max Act: 9.2244. Min Act: -0.1700
Data Index: 3221803 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2244. Min Range: -10.2244
Max Act: 9.2244. Min Act: -0.1700
Data Index: 3583861 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2244. Min Range: -10.2244
Max Act: 9.1619. Min Act: -0.1700
Data Index: 6925689 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2244. Min Range: -10.2244
Max Act: 9.0994. Min Act: -0.1700
Data Index: 29354 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2244. Min Range: -10.2244
Max Act: 9.0369. Min Act: -0.1700
Data Index: 3155954 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2244. Min Range: -10.2244
Max Act: 9.0369. Min Act: -0.1700
Data Index: 6797125 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2244. Min Range: -10.2244
Max Act: 9.0369. Min Act: -0.1700
Data Index: 1992810 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2244. Min Range: -10.2244
Max Act: 9.0994. Min Act: -0.1700
Data Index: 6797123 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2244. Min Range: -10.2244
Max Act: 9.0369. Min Act: -0.1700
Data Index: 6797124 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2244. Min Range: -10.2244
Max Act: 8.9119. Min Act: -0.1700
Data Index: 4056633 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19