Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1647 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4372. Min Range: -6.4372
Max Act: 6.4372. Min Act: -0.1700
Data Index: 1967929 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4372. Min Range: -6.4372
Max Act: 5.8747. Min Act: -0.1700
Data Index: 7045935 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4372. Min Range: -6.4372
Max Act: 5.8434. Min Act: -0.1700
Data Index: 4815459 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4372. Min Range: -6.4372
Max Act: 5.8434. Min Act: -0.1700
Data Index: 3805188 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4372. Min Range: -6.4372
Max Act: 5.8122. Min Act: -0.1700
Data Index: 4691572 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4372. Min Range: -6.4372
Max Act: 5.6872. Min Act: -0.1700
Data Index: 2932170 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4372. Min Range: -6.4372
Max Act: 5.6872. Min Act: -0.1700
Data Index: 4211341 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4372. Min Range: -6.4372
Max Act: 5.6872. Min Act: -0.1700
Data Index: 3749537 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4372. Min Range: -6.4372
Max Act: 5.6247. Min Act: -0.1700
Data Index: 2971687 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4372. Min Range: -6.4372
Max Act: 5.5934. Min Act: -0.1700
Data Index: 8293243 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4372. Min Range: -6.4372
Max Act: 5.5934. Min Act: -0.1700
Data Index: 646663 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4372. Min Range: -6.4372
Max Act: 5.5934. Min Act: -0.1700
Data Index: 5066462 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4372. Min Range: -6.4372
Max Act: 5.5622. Min Act: -0.1700
Data Index: 2008121 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4372. Min Range: -6.4372
Max Act: 5.4684. Min Act: -0.1700
Data Index: 7975337 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4372. Min Range: -6.4372
Max Act: 5.4684. Min Act: -0.1700
Data Index: 4676031 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4372. Min Range: -6.4372
Max Act: 5.4684. Min Act: -0.1700
Data Index: 7797901 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4372. Min Range: -6.4372
Max Act: 5.4684. Min Act: -0.1700
Data Index: 2720775 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4372. Min Range: -6.4372
Max Act: 5.4684. Min Act: -0.1700
Data Index: 4773048 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4372. Min Range: -6.4372
Max Act: 5.4684. Min Act: -0.1700
Data Index: 3078751 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4372. Min Range: -6.4372
Max Act: 5.4684. Min Act: -0.1700
Data Index: 2505452 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19