Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1871 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3716. Min Range: -6.3716
Max Act: 6.3716. Min Act: -0.1700
Data Index: 4253300 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3716. Min Range: -6.3716
Max Act: 6.1528. Min Act: -0.1700
Data Index: 4622299 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3716. Min Range: -6.3716
Max Act: 5.9966. Min Act: -0.1700
Data Index: 6743030 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3716. Min Range: -6.3716
Max Act: 6.0278. Min Act: -0.1700
Data Index: 2108948 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3716. Min Range: -6.3716
Max Act: 5.9653. Min Act: -0.1700
Data Index: 485576 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3716. Min Range: -6.3716
Max Act: 5.9653. Min Act: -0.1700
Data Index: 6725581 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3716. Min Range: -6.3716
Max Act: 5.9653. Min Act: -0.1700
Data Index: 7838481 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3716. Min Range: -6.3716
Max Act: 5.9653. Min Act: -0.1700
Data Index: 420144 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3716. Min Range: -6.3716
Max Act: 5.9341. Min Act: -0.1700
Data Index: 2907792 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3716. Min Range: -6.3716
Max Act: 5.9341. Min Act: -0.1700
Data Index: 6803388 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3716. Min Range: -6.3716
Max Act: 5.9341. Min Act: -0.1700
Data Index: 5252246 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3716. Min Range: -6.3716
Max Act: 5.9341. Min Act: -0.1700
Data Index: 3940545 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3716. Min Range: -6.3716
Max Act: 5.9028. Min Act: -0.1700
Data Index: 4299402 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3716. Min Range: -6.3716
Max Act: 5.9028. Min Act: -0.1700
Data Index: 3996994 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3716. Min Range: -6.3716
Max Act: 5.8716. Min Act: -0.1700
Data Index: 549320 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3716. Min Range: -6.3716
Max Act: 5.8403. Min Act: -0.1700
Data Index: 2907789 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3716. Min Range: -6.3716
Max Act: 5.8716. Min Act: -0.1700
Data Index: 5991324 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3716. Min Range: -6.3716
Max Act: 5.8716. Min Act: -0.1700
Data Index: 3543276 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3716. Min Range: -6.3716
Max Act: 5.8403. Min Act: -0.1700
Data Index: 2882043 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3716. Min Range: -6.3716
Max Act: 5.8403. Min Act: -0.1700
Data Index: 5446339 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19