Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3486 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1808. Min Range: -4.1808
Max Act: 4.1808. Min Act: -0.1700
Data Index: 4303157 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1808. Min Range: -4.1808
Max Act: 4.1183. Min Act: -0.1700
Data Index: 3323007 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1808. Min Range: -4.1808
Max Act: 4.0871. Min Act: -0.1700
Data Index: 8784310 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1808. Min Range: -4.1808
Max Act: 4.0558. Min Act: -0.1700
Data Index: 4238056 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1808. Min Range: -4.1808
Max Act: 4.0245. Min Act: -0.1700
Data Index: 7336808 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1808. Min Range: -4.1808
Max Act: 4.0245. Min Act: -0.1700
Data Index: 7546080 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1808. Min Range: -4.1808
Max Act: 3.9933. Min Act: -0.1700
Data Index: 3409775 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1808. Min Range: -4.1808
Max Act: 3.9933. Min Act: -0.1700
Data Index: 167807 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1808. Min Range: -4.1808
Max Act: 3.9933. Min Act: -0.1700
Data Index: 4252290 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1808. Min Range: -4.1808
Max Act: 3.9933. Min Act: -0.1700
Data Index: 7612829 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1808. Min Range: -4.1808
Max Act: 3.9620. Min Act: -0.1700
Data Index: 6757847 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1808. Min Range: -4.1808
Max Act: 3.9620. Min Act: -0.1700
Data Index: 167809 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1808. Min Range: -4.1808
Max Act: 3.9308. Min Act: -0.1700
Data Index: 4473033 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1808. Min Range: -4.1808
Max Act: 3.9308. Min Act: -0.1700
Data Index: 1130122 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1808. Min Range: -4.1808
Max Act: 3.9308. Min Act: -0.1700
Data Index: 3740783 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1808. Min Range: -4.1808
Max Act: 3.9308. Min Act: -0.1700
Data Index: 6298967 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1808. Min Range: -4.1808
Max Act: 3.8995. Min Act: -0.1700
Data Index: 2013095 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1808. Min Range: -4.1808
Max Act: 3.8995. Min Act: -0.1700
Data Index: 7274912 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1808. Min Range: -4.1808
Max Act: 3.8995. Min Act: -0.1700
Data Index: 4814437 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1808. Min Range: -4.1808
Max Act: 3.8995. Min Act: -0.1700
Data Index: 436579 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19