Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2741 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.6019. Min Act: -0.1700
Data Index: 6754740 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.5082. Min Act: -0.1700
Data Index: 4080831 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.5082. Min Act: -0.1700
Data Index: 7128921 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.4144. Min Act: -0.1700
Data Index: 7066470 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.3832. Min Act: -0.1700
Data Index: 5504175 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.3207. Min Act: -0.1700
Data Index: 996810 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.3207. Min Act: -0.1700
Data Index: 6338841 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.3519. Min Act: -0.1700
Data Index: 522169 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.2582. Min Act: -0.1700
Data Index: 4714709 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.2582. Min Act: -0.1700
Data Index: 6665998 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.2269. Min Act: -0.1700
Data Index: 1917560 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.2269. Min Act: -0.1700
Data Index: 902065 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.2269. Min Act: -0.1700
Data Index: 8219165 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.2582. Min Act: -0.1700
Data Index: 8331386 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.1957. Min Act: -0.1700
Data Index: 3866994 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.2269. Min Act: -0.1700
Data Index: 4062505 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.2269. Min Act: -0.1700
Data Index: 2833969 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.1957. Min Act: -0.1700
Data Index: 5278777 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.1957. Min Act: -0.1700
Data Index: 6024714 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.1957. Min Act: -0.1700
Data Index: 3303788 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19