Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1497 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6829. Min Range: -7.6829
Max Act: 7.6829. Min Act: -0.1700
Data Index: 2699736 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6829. Min Range: -7.6829
Max Act: 7.6204. Min Act: -0.1700
Data Index: 3911924 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6829. Min Range: -7.6829
Max Act: 7.5266. Min Act: -0.1700
Data Index: 5395166 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6829. Min Range: -7.6829
Max Act: 7.4954. Min Act: -0.1700
Data Index: 6527669 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6829. Min Range: -7.6829
Max Act: 7.3704. Min Act: -0.1700
Data Index: 8271824 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6829. Min Range: -7.6829
Max Act: 7.3391. Min Act: -0.1700
Data Index: 6867049 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6829. Min Range: -7.6829
Max Act: 7.3079. Min Act: -0.1700
Data Index: 940818 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6829. Min Range: -7.6829
Max Act: 7.2141. Min Act: -0.1700
Data Index: 6609730 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6829. Min Range: -7.6829
Max Act: 7.2141. Min Act: -0.1700
Data Index: 6811474 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6829. Min Range: -7.6829
Max Act: 7.1829. Min Act: -0.1700
Data Index: 7239401 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6829. Min Range: -7.6829
Max Act: 7.2141. Min Act: -0.1700
Data Index: 5825076 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6829. Min Range: -7.6829
Max Act: 7.2141. Min Act: -0.1700
Data Index: 636129 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6829. Min Range: -7.6829
Max Act: 7.1516. Min Act: -0.1700
Data Index: 4443059 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6829. Min Range: -7.6829
Max Act: 7.1516. Min Act: -0.1700
Data Index: 373279 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6829. Min Range: -7.6829
Max Act: 7.1204. Min Act: -0.1700
Data Index: 6847814 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6829. Min Range: -7.6829
Max Act: 7.1829. Min Act: -0.1700
Data Index: 5703116 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6829. Min Range: -7.6829
Max Act: 7.1829. Min Act: -0.1700
Data Index: 4896017 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6829. Min Range: -7.6829
Max Act: 7.1204. Min Act: -0.1700
Data Index: 5072442 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6829. Min Range: -7.6829
Max Act: 7.1204. Min Act: -0.1700
Data Index: 6694997 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6829. Min Range: -7.6829
Max Act: 7.0891. Min Act: -0.1700
Data Index: 1069574 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19