Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3093 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7796. Min Range: -4.7796
Max Act: 4.7796. Min Act: -0.1700
Data Index: 2120901 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7796. Min Range: -4.7796
Max Act: 4.6546. Min Act: -0.1700
Data Index: 2120899 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7796. Min Range: -4.7796
Max Act: 4.4671. Min Act: -0.1700
Data Index: 1463865 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7796. Min Range: -4.7796
Max Act: 4.2796. Min Act: -0.1700
Data Index: 4607826 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7796. Min Range: -4.7796
Max Act: 4.1546. Min Act: -0.1700
Data Index: 6515812 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7796. Min Range: -4.7796
Max Act: 4.1546. Min Act: -0.1700
Data Index: 5786483 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7796. Min Range: -4.7796
Max Act: 4.0608. Min Act: -0.1700
Data Index: 3495408 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7796. Min Range: -4.7796
Max Act: 4.0608. Min Act: -0.1700
Data Index: 7401870 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7796. Min Range: -4.7796
Max Act: 4.0296. Min Act: -0.1700
Data Index: 3549030 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7796. Min Range: -4.7796
Max Act: 3.9983. Min Act: -0.1700
Data Index: 7561966 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7796. Min Range: -4.7796
Max Act: 4.0296. Min Act: -0.1700
Data Index: 2013128 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7796. Min Range: -4.7796
Max Act: 4.0296. Min Act: -0.1700
Data Index: 8790661 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7796. Min Range: -4.7796
Max Act: 4.0296. Min Act: -0.1700
Data Index: 334153 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7796. Min Range: -4.7796
Max Act: 4.0608. Min Act: -0.1700
Data Index: 5731690 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7796. Min Range: -4.7796
Max Act: 4.0296. Min Act: -0.1700
Data Index: 6524594 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7796. Min Range: -4.7796
Max Act: 3.9983. Min Act: -0.1700
Data Index: 6255724 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7796. Min Range: -4.7796
Max Act: 4.0296. Min Act: -0.1700
Data Index: 6080539 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7796. Min Range: -4.7796
Max Act: 4.0296. Min Act: -0.1700
Data Index: 1941224 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7796. Min Range: -4.7796
Max Act: 4.0296. Min Act: -0.1700
Data Index: 6164357 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7796. Min Range: -4.7796
Max Act: 3.9670. Min Act: -0.1700
Data Index: 125298 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19