Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4167 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4996. Min Range: -7.4996
Max Act: 7.4996. Min Act: -0.1700
Data Index: 1160649 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4996. Min Range: -7.4996
Max Act: 6.8746. Min Act: -0.1700
Data Index: 6444841 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4996. Min Range: -7.4996
Max Act: 6.8746. Min Act: -0.1700
Data Index: 4550129 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4996. Min Range: -7.4996
Max Act: 6.8433. Min Act: -0.1700
Data Index: 1654219 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4996. Min Range: -7.4996
Max Act: 6.7496. Min Act: -0.1700
Data Index: 7204095 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4996. Min Range: -7.4996
Max Act: 6.6871. Min Act: -0.1700
Data Index: 5710121 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4996. Min Range: -7.4996
Max Act: 6.7183. Min Act: -0.1700
Data Index: 5829862 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4996. Min Range: -7.4996
Max Act: 6.6871. Min Act: -0.1700
Data Index: 5504634 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4996. Min Range: -7.4996
Max Act: 6.6871. Min Act: -0.1700
Data Index: 176326 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4996. Min Range: -7.4996
Max Act: 6.7183. Min Act: -0.1700
Data Index: 1666192 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4996. Min Range: -7.4996
Max Act: 6.7183. Min Act: -0.1700
Data Index: 7509378 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4996. Min Range: -7.4996
Max Act: 6.6558. Min Act: -0.1700
Data Index: 3446331 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4996. Min Range: -7.4996
Max Act: 6.6558. Min Act: -0.1700
Data Index: 6809358 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4996. Min Range: -7.4996
Max Act: 6.5933. Min Act: -0.1700
Data Index: 6772224 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4996. Min Range: -7.4996
Max Act: 6.6558. Min Act: -0.1700
Data Index: 2304896 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4996. Min Range: -7.4996
Max Act: 6.5933. Min Act: -0.1700
Data Index: 3829551 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4996. Min Range: -7.4996
Max Act: 6.5933. Min Act: -0.1700
Data Index: 6979087 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4996. Min Range: -7.4996
Max Act: 6.5621. Min Act: -0.1700
Data Index: 4058350 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4996. Min Range: -7.4996
Max Act: 6.5621. Min Act: -0.1700
Data Index: 3944989 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4996. Min Range: -7.4996
Max Act: 6.5621. Min Act: -0.1700
Data Index: 2246757 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19