Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2551 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.4307. Min Act: -0.1700
Data Index: 8722998 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.4307. Min Act: -0.1700
Data Index: 430379 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.4307. Min Act: -0.1700
Data Index: 2804719 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.3682. Min Act: -0.1700
Data Index: 6150958 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2745. Min Act: -0.1700
Data Index: 4893200 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2745. Min Act: -0.1700
Data Index: 4563485 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2432. Min Act: -0.1700
Data Index: 7144245 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2120. Min Act: -0.1700
Data Index: 3816249 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2120. Min Act: -0.1700
Data Index: 900007 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2120. Min Act: -0.1700
Data Index: 1509229 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.1807. Min Act: -0.1700
Data Index: 7488584 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.1807. Min Act: -0.1700
Data Index: 2070046 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.1495. Min Act: -0.1700
Data Index: 974468 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.1495. Min Act: -0.1700
Data Index: 4204180 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.1495. Min Act: -0.1700
Data Index: 6829227 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.0870. Min Act: -0.1700
Data Index: 5044957 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.0870. Min Act: -0.1700
Data Index: 6226267 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.0870. Min Act: -0.1700
Data Index: 4926525 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.0557. Min Act: -0.1700
Data Index: 2990461 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.0557. Min Act: -0.1700
Data Index: 4700910 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19