Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7644. Min Range: -1.7644
Max Act: 1.7644. Min Act: -0.1700
Data Index: 6822936 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7644. Min Range: -1.7644
Max Act: 1.6778. Min Act: -0.1684
Data Index: 6942837 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7644. Min Range: -1.7644
Max Act: 1.6952. Min Act: -0.1700
Data Index: 585232 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7644. Min Range: -1.7644
Max Act: 1.6604. Min Act: -0.1700
Data Index: 2971880 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7644. Min Range: -1.7644
Max Act: 1.6604. Min Act: -0.1700
Data Index: 929086 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7644. Min Range: -1.7644
Max Act: 1.6256. Min Act: -0.1700
Data Index: 6238317 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7644. Min Range: -1.7644
Max Act: 1.6256. Min Act: -0.1700
Data Index: 1441082 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7644. Min Range: -1.7644
Max Act: 1.6081. Min Act: -0.1699
Data Index: 3826581 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7644. Min Range: -1.7644
Max Act: 1.6430. Min Act: -0.1700
Data Index: 2897778 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7644. Min Range: -1.7644
Max Act: 1.5907. Min Act: -0.1699
Data Index: 2317545 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7644. Min Range: -1.7644
Max Act: 1.6081. Min Act: -0.1700
Data Index: 8012812 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7644. Min Range: -1.7644
Max Act: 1.5907. Min Act: -0.1700
Data Index: 2154330 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7644. Min Range: -1.7644
Max Act: 1.5732. Min Act: -0.1696
Data Index: 1039411 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7644. Min Range: -1.7644
Max Act: 1.5907. Min Act: -0.1698
Data Index: 929088 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7644. Min Range: -1.7644
Max Act: 1.5907. Min Act: -0.1700
Data Index: 539311 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7644. Min Range: -1.7644
Max Act: 1.5732. Min Act: -0.1699
Data Index: 7877073 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7644. Min Range: -1.7644
Max Act: 1.5732. Min Act: -0.1700
Data Index: 3190961 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7644. Min Range: -1.7644
Max Act: 1.5732. Min Act: -0.1696
Data Index: 2558711 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7644. Min Range: -1.7644
Max Act: 1.5907. Min Act: -0.1696
Data Index: 6347874 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7644. Min Range: -1.7644
Max Act: 1.5557. Min Act: -0.1700
Data Index: 2142275 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19