Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2125 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4533. Min Range: -7.4533
Max Act: 7.4533. Min Act: -0.1700
Data Index: 6362356 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4533. Min Range: -7.4533
Max Act: 7.0471. Min Act: -0.1700
Data Index: 4885212 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4533. Min Range: -7.4533
Max Act: 6.8596. Min Act: -0.1700
Data Index: 1751451 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4533. Min Range: -7.4533
Max Act: 6.7971. Min Act: -0.1700
Data Index: 4828905 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4533. Min Range: -7.4533
Max Act: 6.7346. Min Act: -0.1700
Data Index: 1304115 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4533. Min Range: -7.4533
Max Act: 6.6721. Min Act: -0.1700
Data Index: 107543 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4533. Min Range: -7.4533
Max Act: 6.6721. Min Act: -0.1700
Data Index: 802597 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4533. Min Range: -7.4533
Max Act: 6.6096. Min Act: -0.1700
Data Index: 6907333 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4533. Min Range: -7.4533
Max Act: 6.5783. Min Act: -0.1700
Data Index: 5225454 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4533. Min Range: -7.4533
Max Act: 6.5783. Min Act: -0.1700
Data Index: 4397088 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4533. Min Range: -7.4533
Max Act: 6.5471. Min Act: -0.1700
Data Index: 7589324 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4533. Min Range: -7.4533
Max Act: 6.5471. Min Act: -0.1700
Data Index: 670830 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4533. Min Range: -7.4533
Max Act: 6.5471. Min Act: -0.1700
Data Index: 5256050 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4533. Min Range: -7.4533
Max Act: 6.5158. Min Act: -0.1700
Data Index: 2232450 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4533. Min Range: -7.4533
Max Act: 6.5158. Min Act: -0.1700
Data Index: 5056931 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4533. Min Range: -7.4533
Max Act: 6.4846. Min Act: -0.1700
Data Index: 6072185 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4533. Min Range: -7.4533
Max Act: 6.4846. Min Act: -0.1700
Data Index: 5853606 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4533. Min Range: -7.4533
Max Act: 6.4533. Min Act: -0.1700
Data Index: 1901797 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4533. Min Range: -7.4533
Max Act: 6.4221. Min Act: -0.1700
Data Index: 6282465 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4533. Min Range: -7.4533
Max Act: 6.4221. Min Act: -0.1700
Data Index: 979060 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19