Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2308 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.8956. Min Act: -0.1700
Data Index: 7510978 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.8643. Min Act: -0.1700
Data Index: 7969135 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.8330. Min Act: -0.1700
Data Index: 4518603 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.7705. Min Act: -0.1700
Data Index: 8732136 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.7705. Min Act: -0.1700
Data Index: 6877536 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.7392. Min Act: -0.1700
Data Index: 974397 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.7079. Min Act: -0.1700
Data Index: 4815248 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.7392. Min Act: -0.1700
Data Index: 5078082 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.6766. Min Act: -0.1700
Data Index: 5882859 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.6453. Min Act: -0.1700
Data Index: 108558 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.6140. Min Act: -0.1700
Data Index: 2313831 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.6453. Min Act: -0.1700
Data Index: 1603275 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.6140. Min Act: -0.1700
Data Index: 1494615 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.6453. Min Act: -0.1700
Data Index: 2800747 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.6453. Min Act: -0.1700
Data Index: 5556525 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.6453. Min Act: -0.1700
Data Index: 4028075 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.6453. Min Act: -0.1700
Data Index: 7401841 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.6453. Min Act: -0.1700
Data Index: 4722 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.6140. Min Act: -0.1700
Data Index: 5259949 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.6140. Min Act: -0.1700
Data Index: 6523859 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19