Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4953 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2984. Min Range: -2.2984
Max Act: 2.2984. Min Act: -0.1700
Data Index: 1214502 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2984. Min Range: -2.2984
Max Act: 2.2654. Min Act: -0.1700
Data Index: 5407935 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2984. Min Range: -2.2984
Max Act: 2.2654. Min Act: -0.1700
Data Index: 4547566 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2984. Min Range: -2.2984
Max Act: 2.2489. Min Act: -0.1700
Data Index: 2542683 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2984. Min Range: -2.2984
Max Act: 2.2489. Min Act: -0.1700
Data Index: 8158292 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2984. Min Range: -2.2984
Max Act: 2.2324. Min Act: -0.1700
Data Index: 633975 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2984. Min Range: -2.2984
Max Act: 2.1993. Min Act: -0.1700
Data Index: 1124610 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2984. Min Range: -2.2984
Max Act: 2.1494. Min Act: -0.1700
Data Index: 5559987 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2984. Min Range: -2.2984
Max Act: 2.1494. Min Act: -0.1700
Data Index: 6141125 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2984. Min Range: -2.2984
Max Act: 2.1327. Min Act: -0.1700
Data Index: 4510917 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2984. Min Range: -2.2984
Max Act: 2.1327. Min Act: -0.1700
Data Index: 7690890 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2984. Min Range: -2.2984
Max Act: 2.0657. Min Act: -0.1700
Data Index: 1661742 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2984. Min Range: -2.2984
Max Act: 2.0489. Min Act: -0.1700
Data Index: 8030000 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2984. Min Range: -2.2984
Max Act: 2.0489. Min Act: -0.1700
Data Index: 5261421 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2984. Min Range: -2.2984
Max Act: 1.9983. Min Act: -0.1700
Data Index: 6899567 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2984. Min Range: -2.2984
Max Act: 1.9983. Min Act: -0.1700
Data Index: 747162 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2984. Min Range: -2.2984
Max Act: 1.9814. Min Act: -0.1700
Data Index: 1294847 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2984. Min Range: -2.2984
Max Act: 1.9814. Min Act: -0.1700
Data Index: 5517935 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2984. Min Range: -2.2984
Max Act: 1.9814. Min Act: -0.1700
Data Index: 2668518 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2984. Min Range: -2.2984
Max Act: 1.9644. Min Act: -0.1700
Data Index: 85033 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19