Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2745 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1652. Min Act: -0.1700
Data Index: 7963571 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1027. Min Act: -0.1700
Data Index: 7164192 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1027. Min Act: -0.1700
Data Index: 654054 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1027. Min Act: -0.1700
Data Index: 1809884 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1027. Min Act: -0.1700
Data Index: 2943088 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1027. Min Act: -0.1700
Data Index: 6280516 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1027. Min Act: -0.1700
Data Index: 8127540 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1027. Min Act: -0.1695
Data Index: 6321472 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1027. Min Act: -0.1700
Data Index: 6772277 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1027. Min Act: -0.1700
Data Index: 7157896 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0715. Min Act: -0.1700
Data Index: 1108162 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0715. Min Act: -0.1699
Data Index: 7826061 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0715. Min Act: -0.1700
Data Index: 5466406 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0402. Min Act: -0.1700
Data Index: 2909069 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0090. Min Act: -0.1700
Data Index: 5552746 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0090. Min Act: -0.1700
Data Index: 5099085 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0090. Min Act: -0.1700
Data Index: 6744275 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0090. Min Act: -0.1700
Data Index: 8003542 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1652. Min Range: -5.1652
Max Act: 4.9777. Min Act: -0.1700
Data Index: 3559105 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1652. Min Range: -5.1652
Max Act: 4.9465. Min Act: -0.1700
Data Index: 244410 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19