Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1803 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9880. Min Range: -5.9880
Max Act: 5.9880. Min Act: -0.1700
Data Index: 7551766 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9880. Min Range: -5.9880
Max Act: 5.9568. Min Act: -0.1700
Data Index: 467244 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9880. Min Range: -5.9880
Max Act: 5.8630. Min Act: -0.1700
Data Index: 7603896 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9880. Min Range: -5.9880
Max Act: 5.8005. Min Act: -0.1700
Data Index: 5563671 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9880. Min Range: -5.9880
Max Act: 5.7693. Min Act: -0.1700
Data Index: 1531786 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9880. Min Range: -5.9880
Max Act: 5.7693. Min Act: -0.1700
Data Index: 6980180 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9880. Min Range: -5.9880
Max Act: 5.7380. Min Act: -0.1700
Data Index: 7540793 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9880. Min Range: -5.9880
Max Act: 5.6755. Min Act: -0.1700
Data Index: 4477989 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9880. Min Range: -5.9880
Max Act: 5.6755. Min Act: -0.1700
Data Index: 78060 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9880. Min Range: -5.9880
Max Act: 5.6755. Min Act: -0.1700
Data Index: 6659226 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9880. Min Range: -5.9880
Max Act: 5.6755. Min Act: -0.1700
Data Index: 6407877 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9880. Min Range: -5.9880
Max Act: 5.6443. Min Act: -0.1700
Data Index: 4664008 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9880. Min Range: -5.9880
Max Act: 5.6443. Min Act: -0.1700
Data Index: 759588 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9880. Min Range: -5.9880
Max Act: 5.6443. Min Act: -0.1700
Data Index: 5475990 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9880. Min Range: -5.9880
Max Act: 5.6130. Min Act: -0.1700
Data Index: 7967074 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9880. Min Range: -5.9880
Max Act: 5.6443. Min Act: -0.1700
Data Index: 759578 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9880. Min Range: -5.9880
Max Act: 5.5818. Min Act: -0.1700
Data Index: 7148605 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9880. Min Range: -5.9880
Max Act: 5.5818. Min Act: -0.1700
Data Index: 6153780 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9880. Min Range: -5.9880
Max Act: 5.5818. Min Act: -0.1700
Data Index: 2607405 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9880. Min Range: -5.9880
Max Act: 5.6130. Min Act: -0.1700
Data Index: 2112611 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19