Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4016 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.3010. Min Act: -0.1700
Data Index: 7750063 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.3010. Min Act: -0.1700
Data Index: 1650955 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.2698. Min Act: -0.1700
Data Index: 5636112 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.2073. Min Act: -0.1700
Data Index: 2980869 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.2073. Min Act: -0.1700
Data Index: 5636115 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.1448. Min Act: -0.1700
Data Index: 4200863 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.1760. Min Act: -0.1700
Data Index: 7596557 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.1760. Min Act: -0.1700
Data Index: 5834598 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.1760. Min Act: -0.1700
Data Index: 7596560 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.1448. Min Act: -0.1700
Data Index: 5636113 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.1448. Min Act: -0.1700
Data Index: 7596556 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.1448. Min Act: -0.1700
Data Index: 1891680 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.1448. Min Act: -0.1700
Data Index: 4678717 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.1448. Min Act: -0.1700
Data Index: 2407083 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.1448. Min Act: -0.1700
Data Index: 7596558 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.1135. Min Act: -0.1700
Data Index: 207783 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.1135. Min Act: -0.1700
Data Index: 6168063 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.1135. Min Act: -0.1700
Data Index: 4817626 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.0823. Min Act: -0.1700
Data Index: 1654120 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3010. Min Range: -5.3010
Max Act: 5.1135. Min Act: -0.1700
Data Index: 7596561 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19