Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3703 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6819. Min Range: -5.6819
Max Act: 5.6819. Min Act: -0.1700
Data Index: 1759465 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6819. Min Range: -5.6819
Max Act: 5.5882. Min Act: -0.1700
Data Index: 3015109 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6819. Min Range: -5.6819
Max Act: 5.5882. Min Act: -0.1700
Data Index: 4481814 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6819. Min Range: -5.6819
Max Act: 5.5569. Min Act: -0.1700
Data Index: 1837131 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6819. Min Range: -5.6819
Max Act: 5.5569. Min Act: -0.1700
Data Index: 8360445 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6819. Min Range: -5.6819
Max Act: 5.5569. Min Act: -0.1700
Data Index: 4665373 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6819. Min Range: -5.6819
Max Act: 5.5569. Min Act: -0.1700
Data Index: 8720299 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6819. Min Range: -5.6819
Max Act: 5.5257. Min Act: -0.1700
Data Index: 220225 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6819. Min Range: -5.6819
Max Act: 5.5257. Min Act: -0.1700
Data Index: 163179 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6819. Min Range: -5.6819
Max Act: 5.5257. Min Act: -0.1700
Data Index: 637827 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6819. Min Range: -5.6819
Max Act: 5.5257. Min Act: -0.1700
Data Index: 4567851 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6819. Min Range: -5.6819
Max Act: 5.4944. Min Act: -0.1700
Data Index: 8165876 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6819. Min Range: -5.6819
Max Act: 5.4944. Min Act: -0.1700
Data Index: 1993238 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6819. Min Range: -5.6819
Max Act: 5.5569. Min Act: -0.1700
Data Index: 2811651 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6819. Min Range: -5.6819
Max Act: 5.4944. Min Act: -0.1700
Data Index: 4950960 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6819. Min Range: -5.6819
Max Act: 5.4944. Min Act: -0.1700
Data Index: 5840637 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6819. Min Range: -5.6819
Max Act: 5.4944. Min Act: -0.1700
Data Index: 637829 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6819. Min Range: -5.6819
Max Act: 5.4632. Min Act: -0.1700
Data Index: 2505504 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6819. Min Range: -5.6819
Max Act: 5.4944. Min Act: -0.1700
Data Index: 7011141 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6819. Min Range: -5.6819
Max Act: 5.4944. Min Act: -0.1700
Data Index: 1819868 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19