Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3076 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6743. Min Range: -5.6743
Max Act: 5.6743. Min Act: -0.1700
Data Index: 2132194 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6743. Min Range: -5.6743
Max Act: 5.2681. Min Act: -0.1700
Data Index: 2502704 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6743. Min Range: -5.6743
Max Act: 5.1118. Min Act: -0.1700
Data Index: 2861755 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6743. Min Range: -5.6743
Max Act: 5.0806. Min Act: -0.1700
Data Index: 8526435 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6743. Min Range: -5.6743
Max Act: 5.1118. Min Act: -0.1700
Data Index: 8636926 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6743. Min Range: -5.6743
Max Act: 5.1118. Min Act: -0.1700
Data Index: 3958958 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6743. Min Range: -5.6743
Max Act: 5.1118. Min Act: -0.1700
Data Index: 1292690 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6743. Min Range: -5.6743
Max Act: 5.0806. Min Act: -0.1700
Data Index: 3304317 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6743. Min Range: -5.6743
Max Act: 5.0493. Min Act: -0.1700
Data Index: 4628234 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6743. Min Range: -5.6743
Max Act: 5.0181. Min Act: -0.1700
Data Index: 6758205 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6743. Min Range: -5.6743
Max Act: 4.9556. Min Act: -0.1700
Data Index: 1526914 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6743. Min Range: -5.6743
Max Act: 4.9868. Min Act: -0.1700
Data Index: 8325172 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6743. Min Range: -5.6743
Max Act: 4.9556. Min Act: -0.1700
Data Index: 667041 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6743. Min Range: -5.6743
Max Act: 4.9556. Min Act: -0.1700
Data Index: 5844350 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6743. Min Range: -5.6743
Max Act: 4.9556. Min Act: -0.1700
Data Index: 7893145 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6743. Min Range: -5.6743
Max Act: 4.9556. Min Act: -0.1700
Data Index: 6289996 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6743. Min Range: -5.6743
Max Act: 4.9243. Min Act: -0.1700
Data Index: 1492509 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6743. Min Range: -5.6743
Max Act: 4.8618. Min Act: -0.1700
Data Index: 657343 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6743. Min Range: -5.6743
Max Act: 4.8931. Min Act: -0.1700
Data Index: 6475680 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6743. Min Range: -5.6743
Max Act: 4.8931. Min Act: -0.1700
Data Index: 6002740 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19