Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2708 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3787. Min Range: -3.3787
Max Act: 3.3787. Min Act: -0.1700
Data Index: 8791859 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3787. Min Range: -3.3787
Max Act: 3.3003. Min Act: -0.1700
Data Index: 2710888 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3787. Min Range: -3.3787
Max Act: 3.2531. Min Act: -0.1700
Data Index: 7144030 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3787. Min Range: -3.3787
Max Act: 3.2060. Min Act: -0.1700
Data Index: 4718117 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3787. Min Range: -3.3787
Max Act: 3.2060. Min Act: -0.1700
Data Index: 3046465 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3787. Min Range: -3.3787
Max Act: 3.1588. Min Act: -0.1700
Data Index: 3165341 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3787. Min Range: -3.3787
Max Act: 3.1431. Min Act: -0.1700
Data Index: 7530604 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3787. Min Range: -3.3787
Max Act: 3.1588. Min Act: -0.1700
Data Index: 633587 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3787. Min Range: -3.3787
Max Act: 3.1273. Min Act: -0.1700
Data Index: 4069959 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3787. Min Range: -3.3787
Max Act: 3.1588. Min Act: -0.1700
Data Index: 7094829 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3787. Min Range: -3.3787
Max Act: 3.1116. Min Act: -0.1700
Data Index: 478201 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3787. Min Range: -3.3787
Max Act: 3.1116. Min Act: -0.1700
Data Index: 1457329 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3787. Min Range: -3.3787
Max Act: 3.1116. Min Act: -0.1700
Data Index: 4221526 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3787. Min Range: -3.3787
Max Act: 3.1116. Min Act: -0.1700
Data Index: 7144024 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3787. Min Range: -3.3787
Max Act: 3.0958. Min Act: -0.1700
Data Index: 898807 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3787. Min Range: -3.3787
Max Act: 3.0958. Min Act: -0.1700
Data Index: 7453724 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3787. Min Range: -3.3787
Max Act: 3.0958. Min Act: -0.1700
Data Index: 2456721 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3787. Min Range: -3.3787
Max Act: 3.0958. Min Act: -0.1700
Data Index: 280692 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3787. Min Range: -3.3787
Max Act: 3.0800. Min Act: -0.1700
Data Index: 7820923 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3787. Min Range: -3.3787
Max Act: 3.0800. Min Act: -0.1700
Data Index: 8639603 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19