Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4952 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9126. Min Range: -9.9126
Max Act: 9.9126. Min Act: -0.1700
Data Index: 1289629 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9126. Min Range: -9.9126
Max Act: 9.7876. Min Act: -0.1700
Data Index: 6994068 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9126. Min Range: -9.9126
Max Act: 9.6626. Min Act: -0.1700
Data Index: 2508086 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9126. Min Range: -9.9126
Max Act: 9.7251. Min Act: -0.1700
Data Index: 3609907 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9126. Min Range: -9.9126
Max Act: 9.6626. Min Act: -0.1700
Data Index: 1023125 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9126. Min Range: -9.9126
Max Act: 9.6626. Min Act: -0.1700
Data Index: 7407631 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9126. Min Range: -9.9126
Max Act: 9.6001. Min Act: -0.1700
Data Index: 5730920 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9126. Min Range: -9.9126
Max Act: 9.6001. Min Act: -0.1700
Data Index: 2312339 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9126. Min Range: -9.9126
Max Act: 9.6001. Min Act: -0.1700
Data Index: 8320748 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9126. Min Range: -9.9126
Max Act: 9.5376. Min Act: -0.1700
Data Index: 2885723 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9126. Min Range: -9.9126
Max Act: 9.5376. Min Act: -0.1700
Data Index: 7244266 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9126. Min Range: -9.9126
Max Act: 9.5376. Min Act: -0.1700
Data Index: 5649684 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9126. Min Range: -9.9126
Max Act: 9.5376. Min Act: -0.1700
Data Index: 2312342 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9126. Min Range: -9.9126
Max Act: 9.4751. Min Act: -0.1700
Data Index: 2312330 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9126. Min Range: -9.9126
Max Act: 9.5376. Min Act: -0.1700
Data Index: 955062 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9126. Min Range: -9.9126
Max Act: 9.4751. Min Act: -0.1700
Data Index: 3366456 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9126. Min Range: -9.9126
Max Act: 9.4751. Min Act: -0.1700
Data Index: 7582155 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9126. Min Range: -9.9126
Max Act: 9.4751. Min Act: -0.1700
Data Index: 5790498 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9126. Min Range: -9.9126
Max Act: 9.4751. Min Act: -0.1700
Data Index: 2885719 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9126. Min Range: -9.9126
Max Act: 9.4126. Min Act: -0.1700
Data Index: 4443970 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19