Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1562 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.6554. Min Act: -0.1700
Data Index: 351081 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.6554. Min Act: -0.1637
Data Index: 4000682 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.6242. Min Act: -0.1699
Data Index: 3459481 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.6242. Min Act: -0.1584
Data Index: 3275892 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.5304. Min Act: -0.1698
Data Index: 3855023 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.5929. Min Act: -0.1698
Data Index: 4168033 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.5304. Min Act: -0.1698
Data Index: 6936442 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.5304. Min Act: -0.1700
Data Index: 7094823 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.5304. Min Act: -0.1699
Data Index: 8107220 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.5304. Min Act: -0.1680
Data Index: 4434125 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.5304. Min Act: -0.1697
Data Index: 1686044 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.4992. Min Act: -0.1700
Data Index: 169269 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.4992. Min Act: -0.1699
Data Index: 5108772 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.4992. Min Act: -0.1695
Data Index: 1456294 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.4992. Min Act: -0.1700
Data Index: 4137411 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.4679. Min Act: -0.1699
Data Index: 4811079 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.4679. Min Act: -0.1700
Data Index: 20270 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.4679. Min Act: -0.1699
Data Index: 4095057 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.4679. Min Act: -0.1697
Data Index: 5327367 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.4367. Min Act: -0.1699
Data Index: 513564 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19