Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3040 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3458. Min Range: -6.3458
Max Act: 6.3458. Min Act: -0.1700
Data Index: 850352 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3458. Min Range: -6.3458
Max Act: 6.0333. Min Act: -0.1700
Data Index: 6959894 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3458. Min Range: -6.3458
Max Act: 6.0020. Min Act: -0.1700
Data Index: 3008096 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3458. Min Range: -6.3458
Max Act: 5.8770. Min Act: -0.1700
Data Index: 6929547 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3458. Min Range: -6.3458
Max Act: 5.8145. Min Act: -0.1700
Data Index: 6192833 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3458. Min Range: -6.3458
Max Act: 5.8145. Min Act: -0.1700
Data Index: 2509886 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3458. Min Range: -6.3458
Max Act: 5.7833. Min Act: -0.1700
Data Index: 8373588 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3458. Min Range: -6.3458
Max Act: 5.7833. Min Act: -0.1700
Data Index: 5834930 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3458. Min Range: -6.3458
Max Act: 5.8145. Min Act: -0.1700
Data Index: 6123965 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3458. Min Range: -6.3458
Max Act: 5.7208. Min Act: -0.1700
Data Index: 2457438 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3458. Min Range: -6.3458
Max Act: 5.6895. Min Act: -0.1700
Data Index: 4518793 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3458. Min Range: -6.3458
Max Act: 5.7208. Min Act: -0.1700
Data Index: 4198941 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3458. Min Range: -6.3458
Max Act: 5.6895. Min Act: -0.1700
Data Index: 894756 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3458. Min Range: -6.3458
Max Act: 5.6583. Min Act: -0.1700
Data Index: 1224587 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3458. Min Range: -6.3458
Max Act: 5.6583. Min Act: -0.1700
Data Index: 7831689 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3458. Min Range: -6.3458
Max Act: 5.6583. Min Act: -0.1700
Data Index: 71809 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3458. Min Range: -6.3458
Max Act: 5.6583. Min Act: -0.1700
Data Index: 8227911 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3458. Min Range: -6.3458
Max Act: 5.6270. Min Act: -0.1700
Data Index: 5700852 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3458. Min Range: -6.3458
Max Act: 5.6270. Min Act: -0.1700
Data Index: 4895334 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3458. Min Range: -6.3458
Max Act: 5.6270. Min Act: -0.1700
Data Index: 4997250 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19