Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3992 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3733. Min Range: -4.3733
Max Act: 4.3733. Min Act: -0.1700
Data Index: 5791941 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3733. Min Range: -4.3733
Max Act: 4.3421. Min Act: -0.1700
Data Index: 5791939 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3733. Min Range: -4.3733
Max Act: 4.3421. Min Act: -0.1700
Data Index: 1754039 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3733. Min Range: -4.3733
Max Act: 4.3108. Min Act: -0.1700
Data Index: 4196654 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3733. Min Range: -4.3733
Max Act: 4.2796. Min Act: -0.1700
Data Index: 7536578 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3733. Min Range: -4.3733
Max Act: 4.2796. Min Act: -0.1700
Data Index: 4479052 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3733. Min Range: -4.3733
Max Act: 4.2483. Min Act: -0.1700
Data Index: 5284342 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3733. Min Range: -4.3733
Max Act: 4.2483. Min Act: -0.1700
Data Index: 4520789 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3733. Min Range: -4.3733
Max Act: 4.2483. Min Act: -0.1700
Data Index: 957698 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3733. Min Range: -4.3733
Max Act: 4.2483. Min Act: -0.1700
Data Index: 7441028 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3733. Min Range: -4.3733
Max Act: 4.2796. Min Act: -0.1700
Data Index: 6983533 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3733. Min Range: -4.3733
Max Act: 4.2171. Min Act: -0.1700
Data Index: 3804653 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3733. Min Range: -4.3733
Max Act: 4.1858. Min Act: -0.1700
Data Index: 6175898 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3733. Min Range: -4.3733
Max Act: 4.1546. Min Act: -0.1700
Data Index: 2719125 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3733. Min Range: -4.3733
Max Act: 4.1546. Min Act: -0.1700
Data Index: 2303476 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3733. Min Range: -4.3733
Max Act: 4.1546. Min Act: -0.1700
Data Index: 3087734 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3733. Min Range: -4.3733
Max Act: 4.0920. Min Act: -0.1700
Data Index: 476440 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3733. Min Range: -4.3733
Max Act: 4.1546. Min Act: -0.1700
Data Index: 552250 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3733. Min Range: -4.3733
Max Act: 4.1233. Min Act: -0.1700
Data Index: 357601 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3733. Min Range: -4.3733
Max Act: 4.1233. Min Act: -0.1700
Data Index: 1887712 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19