Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3400 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2424. Min Range: -2.2424
Max Act: 2.2424. Min Act: -0.1700
Data Index: 2596092 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2424. Min Range: -2.2424
Max Act: 2.2093. Min Act: -0.1700
Data Index: 3170732 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2424. Min Range: -2.2424
Max Act: 2.1927. Min Act: -0.1700
Data Index: 1862477 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2424. Min Range: -2.2424
Max Act: 2.1927. Min Act: -0.1700
Data Index: 1222807 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2424. Min Range: -2.2424
Max Act: 2.1927. Min Act: -0.1700
Data Index: 1128478 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2424. Min Range: -2.2424
Max Act: 2.1761. Min Act: -0.1700
Data Index: 8688032 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2424. Min Range: -2.2424
Max Act: 2.1594. Min Act: -0.1700
Data Index: 5267561 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2424. Min Range: -2.2424
Max Act: 2.1761. Min Act: -0.1700
Data Index: 2218684 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2424. Min Range: -2.2424
Max Act: 2.1761. Min Act: -0.1700
Data Index: 1982541 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2424. Min Range: -2.2424
Max Act: 2.1594. Min Act: -0.1700
Data Index: 6796810 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2424. Min Range: -2.2424
Max Act: 2.1594. Min Act: -0.1700
Data Index: 3888013 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2424. Min Range: -2.2424
Max Act: 2.1594. Min Act: -0.1700
Data Index: 8373913 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2424. Min Range: -2.2424
Max Act: 2.1594. Min Act: -0.1700
Data Index: 6340688 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2424. Min Range: -2.2424
Max Act: 2.1594. Min Act: -0.1700
Data Index: 8332121 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2424. Min Range: -2.2424
Max Act: 2.1428. Min Act: -0.1700
Data Index: 8687306 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2424. Min Range: -2.2424
Max Act: 2.1428. Min Act: -0.1700
Data Index: 902807 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2424. Min Range: -2.2424
Max Act: 2.1261. Min Act: -0.1700
Data Index: 5427243 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2424. Min Range: -2.2424
Max Act: 2.1594. Min Act: -0.1700
Data Index: 2804120 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2424. Min Range: -2.2424
Max Act: 2.1428. Min Act: -0.1700
Data Index: 8688029 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2424. Min Range: -2.2424
Max Act: 2.1428. Min Act: -0.1700
Data Index: 2800568 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19