Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2944 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8978. Min Range: -5.8978
Max Act: 5.8978. Min Act: -0.1344
Data Index: 7644224 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8978. Min Range: -5.8978
Max Act: 5.8041. Min Act: -0.1697
Data Index: 3957490 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8978. Min Range: -5.8978
Max Act: 5.8353. Min Act: -0.1700
Data Index: 446475 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8978. Min Range: -5.8978
Max Act: 5.8353. Min Act: -0.1700
Data Index: 4322935 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8978. Min Range: -5.8978
Max Act: 5.8041. Min Act: -0.1697
Data Index: 3879223 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8978. Min Range: -5.8978
Max Act: 5.7728. Min Act: -0.1686
Data Index: 7967769 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8978. Min Range: -5.8978
Max Act: 5.7728. Min Act: -0.1700
Data Index: 3897159 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8978. Min Range: -5.8978
Max Act: 5.7103. Min Act: -0.1696
Data Index: 7967768 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8978. Min Range: -5.8978
Max Act: 5.7416. Min Act: -0.1698
Data Index: 6248317 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8978. Min Range: -5.8978
Max Act: 5.7103. Min Act: -0.1337
Data Index: 446473 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8978. Min Range: -5.8978
Max Act: 5.7103. Min Act: -0.1700
Data Index: 7644233 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8978. Min Range: -5.8978
Max Act: 5.7103. Min Act: -0.1561
Data Index: 446474 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8978. Min Range: -5.8978
Max Act: 5.7103. Min Act: -0.1698
Data Index: 1817893 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8978. Min Range: -5.8978
Max Act: 5.7416. Min Act: -0.1698
Data Index: 7644225 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8978. Min Range: -5.8978
Max Act: 5.7103. Min Act: -0.1700
Data Index: 1212597 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8978. Min Range: -5.8978
Max Act: 5.7103. Min Act: -0.1700
Data Index: 7967770 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8978. Min Range: -5.8978
Max Act: 5.6791. Min Act: -0.1699
Data Index: 2627857 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8978. Min Range: -5.8978
Max Act: 5.6791. Min Act: -0.1700
Data Index: 8538321 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8978. Min Range: -5.8978
Max Act: 5.6478. Min Act: -0.1700
Data Index: 3879221 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8978. Min Range: -5.8978
Max Act: 5.6478. Min Act: -0.1698
Data Index: 2447635 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19