Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 831 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.0569. Min Range: -1.0569
Max Act: 1.0569. Min Act: -0.1700
Data Index: 6545240 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0569. Min Range: -1.0569
Max Act: 0.9959. Min Act: -0.1700
Data Index: 2656744 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0569. Min Range: -1.0569
Max Act: 0.9959. Min Act: -0.1700
Data Index: 420794 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0569. Min Range: -1.0569
Max Act: 0.9613. Min Act: -0.1700
Data Index: 4011337 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0569. Min Range: -1.0569
Max Act: 0.9613. Min Act: -0.1700
Data Index: 4148591 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0569. Min Range: -1.0569
Max Act: 0.9527. Min Act: -0.1700
Data Index: 6722012 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0569. Min Range: -1.0569
Max Act: 0.9441. Min Act: -0.1700
Data Index: 6649213 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0569. Min Range: -1.0569
Max Act: 0.9527. Min Act: -0.1700
Data Index: 4211008 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0569. Min Range: -1.0569
Max Act: 0.9355. Min Act: -0.1700
Data Index: 1239310 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0569. Min Range: -1.0569
Max Act: 0.9355. Min Act: -0.1700
Data Index: 6105872 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0569. Min Range: -1.0569
Max Act: 0.9269. Min Act: -0.1700
Data Index: 6346055 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0569. Min Range: -1.0569
Max Act: 0.9355. Min Act: -0.1700
Data Index: 5285648 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0569. Min Range: -1.0569
Max Act: 0.9269. Min Act: -0.1700
Data Index: 5743850 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0569. Min Range: -1.0569
Max Act: 0.9183. Min Act: -0.1700
Data Index: 5692622 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0569. Min Range: -1.0569
Max Act: 0.9097. Min Act: -0.1700
Data Index: 1707876 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0569. Min Range: -1.0569
Max Act: 0.9183. Min Act: -0.1700
Data Index: 6045704 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0569. Min Range: -1.0569
Max Act: 0.9011. Min Act: -0.1700
Data Index: 5142339 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0569. Min Range: -1.0569
Max Act: 0.9011. Min Act: -0.1700
Data Index: 7795382 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0569. Min Range: -1.0569
Max Act: 0.8926. Min Act: -0.1700
Data Index: 3933980 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0569. Min Range: -1.0569
Max Act: 0.9011. Min Act: -0.1700
Data Index: 2172284 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19