Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3627 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1292. Min Range: -4.1292
Max Act: 4.1292. Min Act: -0.1700
Data Index: 7344851 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1292. Min Range: -4.1292
Max Act: 4.1292. Min Act: -0.1700
Data Index: 6263516 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1292. Min Range: -4.1292
Max Act: 4.1292. Min Act: -0.1700
Data Index: 7859079 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1292. Min Range: -4.1292
Max Act: 4.0667. Min Act: -0.1700
Data Index: 6432349 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1292. Min Range: -4.1292
Max Act: 4.0354. Min Act: -0.1700
Data Index: 6052776 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1292. Min Range: -4.1292
Max Act: 4.0667. Min Act: -0.1700
Data Index: 5221085 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1292. Min Range: -4.1292
Max Act: 4.0354. Min Act: -0.1700
Data Index: 1716077 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1292. Min Range: -4.1292
Max Act: 4.0354. Min Act: -0.1700
Data Index: 1487960 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1292. Min Range: -4.1292
Max Act: 4.0042. Min Act: -0.1700
Data Index: 7583357 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1292. Min Range: -4.1292
Max Act: 4.0042. Min Act: -0.1700
Data Index: 2147871 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1292. Min Range: -4.1292
Max Act: 3.9729. Min Act: -0.1700
Data Index: 7203012 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1292. Min Range: -4.1292
Max Act: 3.9729. Min Act: -0.1700
Data Index: 5988504 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1292. Min Range: -4.1292
Max Act: 3.9729. Min Act: -0.1700
Data Index: 1082865 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1292. Min Range: -4.1292
Max Act: 3.9729. Min Act: -0.1700
Data Index: 3690386 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1292. Min Range: -4.1292
Max Act: 3.9729. Min Act: -0.1700
Data Index: 4825009 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1292. Min Range: -4.1292
Max Act: 3.9417. Min Act: -0.1700
Data Index: 2218654 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1292. Min Range: -4.1292
Max Act: 3.9104. Min Act: -0.1700
Data Index: 8185068 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1292. Min Range: -4.1292
Max Act: 3.9417. Min Act: -0.1700
Data Index: 3431596 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1292. Min Range: -4.1292
Max Act: 3.9417. Min Act: -0.1700
Data Index: 1688541 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1292. Min Range: -4.1292
Max Act: 3.9417. Min Act: -0.1700
Data Index: 4259086 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #19