Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1172 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5558. Min Range: -5.5558
Max Act: 5.5558. Min Act: -0.1700
Data Index: 8382858 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5558. Min Range: -5.5558
Max Act: 5.4933. Min Act: -0.1700
Data Index: 7908851 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5558. Min Range: -5.5558
Max Act: 5.4308. Min Act: -0.1700
Data Index: 419957 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5558. Min Range: -5.5558
Max Act: 5.3371. Min Act: -0.1700
Data Index: 6997444 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5558. Min Range: -5.5558
Max Act: 5.2746. Min Act: -0.1700
Data Index: 7566950 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5558. Min Range: -5.5558
Max Act: 5.2121. Min Act: -0.1700
Data Index: 57511 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5558. Min Range: -5.5558
Max Act: 5.2433. Min Act: -0.1700
Data Index: 5033221 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5558. Min Range: -5.5558
Max Act: 5.2121. Min Act: -0.1700
Data Index: 2428458 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5558. Min Range: -5.5558
Max Act: 5.2121. Min Act: -0.1700
Data Index: 4206905 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5558. Min Range: -5.5558
Max Act: 5.2121. Min Act: -0.1700
Data Index: 311612 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5558. Min Range: -5.5558
Max Act: 5.2121. Min Act: -0.1700
Data Index: 782217 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5558. Min Range: -5.5558
Max Act: 5.1808. Min Act: -0.1700
Data Index: 8132225 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5558. Min Range: -5.5558
Max Act: 5.1808. Min Act: -0.1700
Data Index: 6172537 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5558. Min Range: -5.5558
Max Act: 5.1808. Min Act: -0.1700
Data Index: 770102 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5558. Min Range: -5.5558
Max Act: 5.1808. Min Act: -0.1700
Data Index: 6866006 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5558. Min Range: -5.5558
Max Act: 5.1496. Min Act: -0.1700
Data Index: 736695 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5558. Min Range: -5.5558
Max Act: 5.1808. Min Act: -0.1700
Data Index: 372902 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5558. Min Range: -5.5558
Max Act: 5.1496. Min Act: -0.1700
Data Index: 5489856 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5558. Min Range: -5.5558
Max Act: 5.1496. Min Act: -0.1700
Data Index: 3920357 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5558. Min Range: -5.5558
Max Act: 5.1183. Min Act: -0.1700
Data Index: 1701801 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19