Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3292 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4017. Min Range: -6.4017
Max Act: 6.4017. Min Act: -0.1700
Data Index: 7385305 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4017. Min Range: -6.4017
Max Act: 6.3704. Min Act: -0.1700
Data Index: 3491109 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4017. Min Range: -6.4017
Max Act: 6.3704. Min Act: -0.1700
Data Index: 885824 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4017. Min Range: -6.4017
Max Act: 6.3704. Min Act: -0.1700
Data Index: 6560359 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4017. Min Range: -6.4017
Max Act: 6.3392. Min Act: -0.1700
Data Index: 5923956 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4017. Min Range: -6.4017
Max Act: 6.3392. Min Act: -0.1700
Data Index: 5923953 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4017. Min Range: -6.4017
Max Act: 6.3392. Min Act: -0.1700
Data Index: 7476692 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4017. Min Range: -6.4017
Max Act: 6.3079. Min Act: -0.1700
Data Index: 2354504 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4017. Min Range: -6.4017
Max Act: 6.2767. Min Act: -0.1700
Data Index: 5923954 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4017. Min Range: -6.4017
Max Act: 6.2767. Min Act: -0.1700
Data Index: 2725311 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4017. Min Range: -6.4017
Max Act: 6.2142. Min Act: -0.1700
Data Index: 885820 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4017. Min Range: -6.4017
Max Act: 6.2142. Min Act: -0.1700
Data Index: 1658296 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4017. Min Range: -6.4017
Max Act: 6.1517. Min Act: -0.1700
Data Index: 5923950 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4017. Min Range: -6.4017
Max Act: 6.1517. Min Act: -0.1700
Data Index: 1787190 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4017. Min Range: -6.4017
Max Act: 6.1517. Min Act: -0.1700
Data Index: 6602532 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4017. Min Range: -6.4017
Max Act: 6.1517. Min Act: -0.1700
Data Index: 885821 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4017. Min Range: -6.4017
Max Act: 6.1517. Min Act: -0.1700
Data Index: 5817789 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4017. Min Range: -6.4017
Max Act: 6.1204. Min Act: -0.1700
Data Index: 1590748 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4017. Min Range: -6.4017
Max Act: 6.1204. Min Act: -0.1700
Data Index: 6611126 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4017. Min Range: -6.4017
Max Act: 6.1204. Min Act: -0.1700
Data Index: 3402976 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19