Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1107 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3957. Min Range: -7.3957
Max Act: 7.3957. Min Act: -0.1700
Data Index: 4715829 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3957. Min Range: -7.3957
Max Act: 7.2394. Min Act: -0.1700
Data Index: 1108106 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3957. Min Range: -7.3957
Max Act: 7.0519. Min Act: -0.1700
Data Index: 2788478 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3957. Min Range: -7.3957
Max Act: 6.9894. Min Act: -0.1700
Data Index: 4898673 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3957. Min Range: -7.3957
Max Act: 6.9269. Min Act: -0.1700
Data Index: 4794834 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3957. Min Range: -7.3957
Max Act: 6.8957. Min Act: -0.1700
Data Index: 4998430 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3957. Min Range: -7.3957
Max Act: 6.8644. Min Act: -0.1700
Data Index: 3842230 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3957. Min Range: -7.3957
Max Act: 6.8332. Min Act: -0.1700
Data Index: 6603166 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3957. Min Range: -7.3957
Max Act: 6.8644. Min Act: -0.1700
Data Index: 1172915 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3957. Min Range: -7.3957
Max Act: 6.8644. Min Act: -0.1700
Data Index: 6568691 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3957. Min Range: -7.3957
Max Act: 6.8332. Min Act: -0.1700
Data Index: 6384235 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3957. Min Range: -7.3957
Max Act: 6.8332. Min Act: -0.1700
Data Index: 7441323 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3957. Min Range: -7.3957
Max Act: 6.8332. Min Act: -0.1700
Data Index: 6603162 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3957. Min Range: -7.3957
Max Act: 6.7082. Min Act: -0.1700
Data Index: 322556 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3957. Min Range: -7.3957
Max Act: 6.7082. Min Act: -0.1700
Data Index: 2788475 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3957. Min Range: -7.3957
Max Act: 6.6769. Min Act: -0.1700
Data Index: 826531 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3957. Min Range: -7.3957
Max Act: 6.6769. Min Act: -0.1700
Data Index: 1316828 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3957. Min Range: -7.3957
Max Act: 6.5832. Min Act: -0.1700
Data Index: 1741736 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3957. Min Range: -7.3957
Max Act: 6.6457. Min Act: -0.1700
Data Index: 3627488 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3957. Min Range: -7.3957
Max Act: 6.6144. Min Act: -0.1700
Data Index: 347806 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19