Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3628 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.8937. Min Range: -0.8937
Max Act: 0.8937. Min Act: -0.1700
Data Index: 4804721 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8937. Min Range: -0.8937
Max Act: 0.8937. Min Act: -0.1700
Data Index: 5840199 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8937. Min Range: -0.8937
Max Act: 0.8767. Min Act: -0.1700
Data Index: 4957178 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8937. Min Range: -0.8937
Max Act: 0.8682. Min Act: -0.1700
Data Index: 2528756 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8937. Min Range: -0.8937
Max Act: 0.8682. Min Act: -0.1700
Data Index: 469409 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8937. Min Range: -0.8937
Max Act: 0.8597. Min Act: -0.1700
Data Index: 1058056 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8937. Min Range: -0.8937
Max Act: 0.8512. Min Act: -0.1700
Data Index: 1892555 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8937. Min Range: -0.8937
Max Act: 0.8597. Min Act: -0.1700
Data Index: 7446096 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8937. Min Range: -0.8937
Max Act: 0.8512. Min Act: -0.1700
Data Index: 6070735 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8937. Min Range: -0.8937
Max Act: 0.8597. Min Act: -0.1700
Data Index: 3428430 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8937. Min Range: -0.8937
Max Act: 0.8427. Min Act: -0.1700
Data Index: 6325358 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8937. Min Range: -0.8937
Max Act: 0.8427. Min Act: -0.1700
Data Index: 8501660 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8937. Min Range: -0.8937
Max Act: 0.8512. Min Act: -0.1700
Data Index: 5786968 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8937. Min Range: -0.8937
Max Act: 0.8512. Min Act: -0.1700
Data Index: 8228606 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8937. Min Range: -0.8937
Max Act: 0.8512. Min Act: -0.1700
Data Index: 1021462 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8937. Min Range: -0.8937
Max Act: 0.8343. Min Act: -0.1700
Data Index: 2084099 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8937. Min Range: -0.8937
Max Act: 0.8343. Min Act: -0.1700
Data Index: 3246502 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8937. Min Range: -0.8937
Max Act: 0.8343. Min Act: -0.1700
Data Index: 246363 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8937. Min Range: -0.8937
Max Act: 0.8343. Min Act: -0.1700
Data Index: 4957177 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8937. Min Range: -0.8937
Max Act: 0.8343. Min Act: -0.1700
Data Index: 4313007 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19