Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2606 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2054. Min Range: -2.2054
Max Act: 2.2054. Min Act: -0.1700
Data Index: 863077 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2054. Min Range: -2.2054
Max Act: 2.0719. Min Act: -0.1700
Data Index: 4925326 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2054. Min Range: -2.2054
Max Act: 2.0719. Min Act: -0.1700
Data Index: 897018 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2054. Min Range: -2.2054
Max Act: 2.0551. Min Act: -0.1700
Data Index: 1526564 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2054. Min Range: -2.2054
Max Act: 2.0383. Min Act: -0.1700
Data Index: 3349586 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2054. Min Range: -2.2054
Max Act: 2.0383. Min Act: -0.1700
Data Index: 3177165 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2054. Min Range: -2.2054
Max Act: 2.0214. Min Act: -0.1700
Data Index: 3460251 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2054. Min Range: -2.2054
Max Act: 2.0214. Min Act: -0.1700
Data Index: 863080 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2054. Min Range: -2.2054
Max Act: 2.0383. Min Act: -0.1699
Data Index: 7360906 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2054. Min Range: -2.2054
Max Act: 1.9877. Min Act: -0.1700
Data Index: 6466868 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2054. Min Range: -2.2054
Max Act: 2.0214. Min Act: -0.1700
Data Index: 8724220 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2054. Min Range: -2.2054
Max Act: 2.0046. Min Act: -0.1700
Data Index: 6548428 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2054. Min Range: -2.2054
Max Act: 2.0046. Min Act: -0.1700
Data Index: 4095634 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2054. Min Range: -2.2054
Max Act: 1.9877. Min Act: -0.1700
Data Index: 3527523 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2054. Min Range: -2.2054
Max Act: 1.9877. Min Act: -0.1700
Data Index: 6380848 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2054. Min Range: -2.2054
Max Act: 1.9877. Min Act: -0.1700
Data Index: 7286770 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2054. Min Range: -2.2054
Max Act: 1.9877. Min Act: -0.1700
Data Index: 4038640 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2054. Min Range: -2.2054
Max Act: 1.9538. Min Act: -0.1700
Data Index: 714111 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2054. Min Range: -2.2054
Max Act: 1.9707. Min Act: -0.1700
Data Index: 7871921 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2054. Min Range: -2.2054
Max Act: 1.9707. Min Act: -0.1700
Data Index: 2963410 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19