Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1665 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6137. Min Range: -1.6137
Max Act: 1.6137. Min Act: -0.1700
Data Index: 8217418 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6137. Min Range: -1.6137
Max Act: 1.5963. Min Act: -0.1700
Data Index: 2954164 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6137. Min Range: -1.6137
Max Act: 1.6050. Min Act: -0.1700
Data Index: 4470692 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6137. Min Range: -1.6137
Max Act: 1.5963. Min Act: -0.1699
Data Index: 7096844 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6137. Min Range: -1.6137
Max Act: 1.5875. Min Act: -0.1699
Data Index: 5793999 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6137. Min Range: -1.6137
Max Act: 1.5788. Min Act: -0.1699
Data Index: 1143460 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6137. Min Range: -1.6137
Max Act: 1.5700. Min Act: -0.1685
Data Index: 7707399 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6137. Min Range: -1.6137
Max Act: 1.5700. Min Act: -0.1609
Data Index: 1991205 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6137. Min Range: -1.6137
Max Act: 1.5350. Min Act: -0.1699
Data Index: 1905269 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6137. Min Range: -1.6137
Max Act: 1.5350. Min Act: -0.1700
Data Index: 5644473 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6137. Min Range: -1.6137
Max Act: 1.5438. Min Act: -0.1615
Data Index: 8218927 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6137. Min Range: -1.6137
Max Act: 1.5350. Min Act: -0.1700
Data Index: 8789377 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6137. Min Range: -1.6137
Max Act: 1.5438. Min Act: -0.1690
Data Index: 2052021 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6137. Min Range: -1.6137
Max Act: 1.5350. Min Act: -0.1700
Data Index: 6111984 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6137. Min Range: -1.6137
Max Act: 1.5175. Min Act: -0.1700
Data Index: 7114794 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6137. Min Range: -1.6137
Max Act: 1.5262. Min Act: -0.1700
Data Index: 595580 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6137. Min Range: -1.6137
Max Act: 1.5350. Min Act: -0.1700
Data Index: 7673407 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6137. Min Range: -1.6137
Max Act: 1.5262. Min Act: -0.1693
Data Index: 1991204 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6137. Min Range: -1.6137
Max Act: 1.4999. Min Act: -0.1690
Data Index: 1765857 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6137. Min Range: -1.6137
Max Act: 1.4999. Min Act: -0.1700
Data Index: 4922333 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19