Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3827 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1203. Min Range: -4.1203
Max Act: 4.1203. Min Act: -0.1700
Data Index: 2437619 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1203. Min Range: -4.1203
Max Act: 4.0265. Min Act: -0.1700
Data Index: 3753081 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1203. Min Range: -4.1203
Max Act: 3.9953. Min Act: -0.1700
Data Index: 2997255 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1203. Min Range: -4.1203
Max Act: 3.9953. Min Act: -0.1700
Data Index: 8177012 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1203. Min Range: -4.1203
Max Act: 3.9953. Min Act: -0.1700
Data Index: 5561952 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1203. Min Range: -4.1203
Max Act: 3.9640. Min Act: -0.1700
Data Index: 2639199 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1203. Min Range: -4.1203
Max Act: 3.9640. Min Act: -0.1700
Data Index: 7329228 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1203. Min Range: -4.1203
Max Act: 3.9640. Min Act: -0.1700
Data Index: 2463921 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1203. Min Range: -4.1203
Max Act: 3.9640. Min Act: -0.1700
Data Index: 5197910 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1203. Min Range: -4.1203
Max Act: 3.9953. Min Act: -0.1700
Data Index: 6800797 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1203. Min Range: -4.1203
Max Act: 3.9327. Min Act: -0.1700
Data Index: 7099156 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1203. Min Range: -4.1203
Max Act: 3.9327. Min Act: -0.1700
Data Index: 582158 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1203. Min Range: -4.1203
Max Act: 3.9327. Min Act: -0.1700
Data Index: 4938834 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1203. Min Range: -4.1203
Max Act: 3.9015. Min Act: -0.1700
Data Index: 4585101 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1203. Min Range: -4.1203
Max Act: 3.9015. Min Act: -0.1700
Data Index: 4335547 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1203. Min Range: -4.1203
Max Act: 3.9015. Min Act: -0.1700
Data Index: 2226411 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1203. Min Range: -4.1203
Max Act: 3.9015. Min Act: -0.1700
Data Index: 4111047 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1203. Min Range: -4.1203
Max Act: 3.9015. Min Act: -0.1700
Data Index: 2105584 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1203. Min Range: -4.1203
Max Act: 3.9327. Min Act: -0.1700
Data Index: 3666802 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1203. Min Range: -4.1203
Max Act: 3.9015. Min Act: -0.1700
Data Index: 1503928 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19