Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2153 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0261. Min Range: -4.0261
Max Act: 3.9636. Min Act: -0.1700
Data Index: 60185 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0261. Min Range: -4.0261
Max Act: 4.0261. Min Act: -0.1700
Data Index: 8004405 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0261. Min Range: -4.0261
Max Act: 3.9636. Min Act: -0.1700
Data Index: 4822493 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0261. Min Range: -4.0261
Max Act: 3.9323. Min Act: -0.1700
Data Index: 826130 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0261. Min Range: -4.0261
Max Act: 3.9323. Min Act: -0.1700
Data Index: 1344127 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0261. Min Range: -4.0261
Max Act: 3.9010. Min Act: -0.1700
Data Index: 4654291 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0261. Min Range: -4.0261
Max Act: 3.9010. Min Act: -0.1700
Data Index: 2136133 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0261. Min Range: -4.0261
Max Act: 3.9010. Min Act: -0.1700
Data Index: 4192633 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0261. Min Range: -4.0261
Max Act: 3.9010. Min Act: -0.1700
Data Index: 6024126 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0261. Min Range: -4.0261
Max Act: 3.8698. Min Act: -0.1700
Data Index: 4733085 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0261. Min Range: -4.0261
Max Act: 3.8698. Min Act: -0.1700
Data Index: 3987447 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0261. Min Range: -4.0261
Max Act: 3.8385. Min Act: -0.1700
Data Index: 4064808 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0261. Min Range: -4.0261
Max Act: 3.9010. Min Act: -0.1700
Data Index: 3450437 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0261. Min Range: -4.0261
Max Act: 3.8698. Min Act: -0.1700
Data Index: 6851665 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0261. Min Range: -4.0261
Max Act: 3.8385. Min Act: -0.1700
Data Index: 66286 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0261. Min Range: -4.0261
Max Act: 3.8385. Min Act: -0.1700
Data Index: 4894139 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0261. Min Range: -4.0261
Max Act: 3.8385. Min Act: -0.1700
Data Index: 5305244 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0261. Min Range: -4.0261
Max Act: 3.8385. Min Act: -0.1700
Data Index: 2464894 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0261. Min Range: -4.0261
Max Act: 3.8698. Min Act: -0.1700
Data Index: 8338860 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0261. Min Range: -4.0261
Max Act: 3.8385. Min Act: -0.1700
Data Index: 733928 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19