Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2128 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4540. Min Range: -5.4540
Max Act: 5.4540. Min Act: -0.1700
Data Index: 5629669 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4540. Min Range: -5.4540
Max Act: 5.2977. Min Act: -0.1700
Data Index: 1111386 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4540. Min Range: -5.4540
Max Act: 5.2977. Min Act: -0.1700
Data Index: 5436953 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4540. Min Range: -5.4540
Max Act: 5.2977. Min Act: -0.1700
Data Index: 5538902 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4540. Min Range: -5.4540
Max Act: 5.2977. Min Act: -0.1700
Data Index: 6684517 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4540. Min Range: -5.4540
Max Act: 5.2665. Min Act: -0.1700
Data Index: 7791979 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4540. Min Range: -5.4540
Max Act: 5.2040. Min Act: -0.1700
Data Index: 4408166 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4540. Min Range: -5.4540
Max Act: 5.1727. Min Act: -0.1700
Data Index: 4266459 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4540. Min Range: -5.4540
Max Act: 5.1102. Min Act: -0.1700
Data Index: 6893353 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4540. Min Range: -5.4540
Max Act: 5.1102. Min Act: -0.1700
Data Index: 6930553 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4540. Min Range: -5.4540
Max Act: 5.1102. Min Act: -0.1700
Data Index: 6801030 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4540. Min Range: -5.4540
Max Act: 5.0477. Min Act: -0.1700
Data Index: 1564942 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4540. Min Range: -5.4540
Max Act: 5.0790. Min Act: -0.1700
Data Index: 2590763 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4540. Min Range: -5.4540
Max Act: 5.0790. Min Act: -0.1700
Data Index: 1656068 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4540. Min Range: -5.4540
Max Act: 5.0790. Min Act: -0.1700
Data Index: 285204 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4540. Min Range: -5.4540
Max Act: 5.1102. Min Act: -0.1700
Data Index: 5667500 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4540. Min Range: -5.4540
Max Act: 5.0477. Min Act: -0.1700
Data Index: 3514470 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4540. Min Range: -5.4540
Max Act: 5.0477. Min Act: -0.1700
Data Index: 3337256 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4540. Min Range: -5.4540
Max Act: 5.0165. Min Act: -0.1700
Data Index: 3694759 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4540. Min Range: -5.4540
Max Act: 5.0165. Min Act: -0.1700
Data Index: 1095060 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19