Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1896 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8937. Min Range: -4.8937
Max Act: 4.8937. Min Act: -0.1700
Data Index: 877171 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8937. Min Range: -4.8937
Max Act: 4.6750. Min Act: -0.1700
Data Index: 748738 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8937. Min Range: -4.8937
Max Act: 4.5812. Min Act: -0.1700
Data Index: 8739138 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8937. Min Range: -4.8937
Max Act: 4.5500. Min Act: -0.1700
Data Index: 7926410 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8937. Min Range: -4.8937
Max Act: 4.5187. Min Act: -0.1700
Data Index: 3182792 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8937. Min Range: -4.8937
Max Act: 4.5187. Min Act: -0.1700
Data Index: 4808937 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8937. Min Range: -4.8937
Max Act: 4.4875. Min Act: -0.1700
Data Index: 6308650 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8937. Min Range: -4.8937
Max Act: 4.4875. Min Act: -0.1700
Data Index: 4219838 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8937. Min Range: -4.8937
Max Act: 4.4875. Min Act: -0.1700
Data Index: 3907117 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8937. Min Range: -4.8937
Max Act: 4.4875. Min Act: -0.1700
Data Index: 4723403 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8937. Min Range: -4.8937
Max Act: 4.4250. Min Act: -0.1700
Data Index: 7842995 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8937. Min Range: -4.8937
Max Act: 4.3937. Min Act: -0.1700
Data Index: 6420255 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8937. Min Range: -4.8937
Max Act: 4.3937. Min Act: -0.1700
Data Index: 7851706 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8937. Min Range: -4.8937
Max Act: 4.3937. Min Act: -0.1700
Data Index: 6657617 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8937. Min Range: -4.8937
Max Act: 4.3937. Min Act: -0.1700
Data Index: 1342920 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8937. Min Range: -4.8937
Max Act: 4.3937. Min Act: -0.1700
Data Index: 4372545 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8937. Min Range: -4.8937
Max Act: 4.3625. Min Act: -0.1700
Data Index: 4233429 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8937. Min Range: -4.8937
Max Act: 4.3625. Min Act: -0.1700
Data Index: 4231438 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8937. Min Range: -4.8937
Max Act: 4.3625. Min Act: -0.1700
Data Index: 1374494 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8937. Min Range: -4.8937
Max Act: 4.3937. Min Act: -0.1700
Data Index: 5842642 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19