Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2997 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1062. Min Range: -7.1062
Max Act: 7.1062. Min Act: -0.1700
Data Index: 2003151 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1062. Min Range: -7.1062
Max Act: 6.7312. Min Act: -0.1700
Data Index: 6697619 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1062. Min Range: -7.1062
Max Act: 6.7000. Min Act: -0.1700
Data Index: 2661720 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1062. Min Range: -7.1062
Max Act: 6.6687. Min Act: -0.1700
Data Index: 6538218 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1062. Min Range: -7.1062
Max Act: 6.6687. Min Act: -0.1700
Data Index: 387099 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1062. Min Range: -7.1062
Max Act: 6.6687. Min Act: -0.1700
Data Index: 5188178 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1062. Min Range: -7.1062
Max Act: 6.6375. Min Act: -0.1700
Data Index: 7931893 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1062. Min Range: -7.1062
Max Act: 6.6375. Min Act: -0.1700
Data Index: 4862423 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1062. Min Range: -7.1062
Max Act: 6.6375. Min Act: -0.1700
Data Index: 8680822 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1062. Min Range: -7.1062
Max Act: 6.6375. Min Act: -0.1700
Data Index: 755952 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1062. Min Range: -7.1062
Max Act: 6.6375. Min Act: -0.1700
Data Index: 5582167 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1062. Min Range: -7.1062
Max Act: 6.6062. Min Act: -0.1700
Data Index: 3821485 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1062. Min Range: -7.1062
Max Act: 6.5437. Min Act: -0.1700
Data Index: 8084331 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1062. Min Range: -7.1062
Max Act: 6.5437. Min Act: -0.1700
Data Index: 3201130 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1062. Min Range: -7.1062
Max Act: 6.5437. Min Act: -0.1700
Data Index: 5732785 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1062. Min Range: -7.1062
Max Act: 6.4812. Min Act: -0.1700
Data Index: 3395956 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1062. Min Range: -7.1062
Max Act: 6.4500. Min Act: -0.1700
Data Index: 3016259 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1062. Min Range: -7.1062
Max Act: 6.4500. Min Act: -0.1700
Data Index: 458304 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1062. Min Range: -7.1062
Max Act: 6.4500. Min Act: -0.1700
Data Index: 2239057 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1062. Min Range: -7.1062
Max Act: 6.4500. Min Act: -0.1700
Data Index: 5662203 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19