Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2580 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.4499. Min Range: -1.4499
Max Act: 1.4499. Min Act: -0.1700
Data Index: 7375722 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4499. Min Range: -1.4499
Max Act: 1.3971. Min Act: -0.1699
Data Index: 3044068 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4499. Min Range: -1.4499
Max Act: 1.4147. Min Act: -0.1700
Data Index: 3913117 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4499. Min Range: -1.4499
Max Act: 1.3795. Min Act: -0.1698
Data Index: 2021745 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4499. Min Range: -1.4499
Max Act: 1.3707. Min Act: -0.1700
Data Index: 4025723 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4499. Min Range: -1.4499
Max Act: 1.3530. Min Act: -0.1700
Data Index: 7481182 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4499. Min Range: -1.4499
Max Act: 1.3618. Min Act: -0.1700
Data Index: 5673442 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4499. Min Range: -1.4499
Max Act: 1.3530. Min Act: -0.1700
Data Index: 3465290 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4499. Min Range: -1.4499
Max Act: 1.3530. Min Act: -0.1700
Data Index: 4090670 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4499. Min Range: -1.4499
Max Act: 1.3442. Min Act: -0.1700
Data Index: 4389245 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4499. Min Range: -1.4499
Max Act: 1.3354. Min Act: -0.1700
Data Index: 4235027 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4499. Min Range: -1.4499
Max Act: 1.3442. Min Act: -0.1700
Data Index: 8037647 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4499. Min Range: -1.4499
Max Act: 1.3178. Min Act: -0.1700
Data Index: 2417028 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4499. Min Range: -1.4499
Max Act: 1.3266. Min Act: -0.1700
Data Index: 7483772 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4499. Min Range: -1.4499
Max Act: 1.3178. Min Act: -0.1700
Data Index: 1173794 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4499. Min Range: -1.4499
Max Act: 1.3266. Min Act: -0.1699
Data Index: 1210047 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4499. Min Range: -1.4499
Max Act: 1.3266. Min Act: -0.1700
Data Index: 89686 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4499. Min Range: -1.4499
Max Act: 1.3266. Min Act: -0.1700
Data Index: 2627517 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4499. Min Range: -1.4499
Max Act: 1.3178. Min Act: -0.1700
Data Index: 5023741 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4499. Min Range: -1.4499
Max Act: 1.3178. Min Act: -0.1684
Data Index: 5989928 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19