Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 490 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4016. Min Range: -9.4016
Max Act: 9.4016. Min Act: -0.1700
Data Index: 7442016 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4016. Min Range: -9.4016
Max Act: 8.9016. Min Act: -0.1700
Data Index: 4158762 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4016. Min Range: -9.4016
Max Act: 8.7141. Min Act: -0.1700
Data Index: 7170538 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4016. Min Range: -9.4016
Max Act: 8.7141. Min Act: -0.1700
Data Index: 5891609 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4016. Min Range: -9.4016
Max Act: 8.6516. Min Act: -0.1700
Data Index: 1150343 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4016. Min Range: -9.4016
Max Act: 8.6516. Min Act: -0.1700
Data Index: 499889 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4016. Min Range: -9.4016
Max Act: 8.5891. Min Act: -0.1700
Data Index: 4997031 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4016. Min Range: -9.4016
Max Act: 8.5891. Min Act: -0.1700
Data Index: 6615175 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4016. Min Range: -9.4016
Max Act: 8.5891. Min Act: -0.1700
Data Index: 1862510 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4016. Min Range: -9.4016
Max Act: 8.5891. Min Act: -0.1700
Data Index: 4070350 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4016. Min Range: -9.4016
Max Act: 8.5266. Min Act: -0.1700
Data Index: 3002582 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4016. Min Range: -9.4016
Max Act: 8.4641. Min Act: -0.1700
Data Index: 5487131 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4016. Min Range: -9.4016
Max Act: 8.4641. Min Act: -0.1700
Data Index: 496728 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4016. Min Range: -9.4016
Max Act: 8.4641. Min Act: -0.1700
Data Index: 8536292 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4016. Min Range: -9.4016
Max Act: 8.4016. Min Act: -0.1700
Data Index: 5536447 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4016. Min Range: -9.4016
Max Act: 8.4016. Min Act: -0.1700
Data Index: 2045357 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4016. Min Range: -9.4016
Max Act: 8.4016. Min Act: -0.1700
Data Index: 227890 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4016. Min Range: -9.4016
Max Act: 8.4016. Min Act: -0.1700
Data Index: 5449935 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4016. Min Range: -9.4016
Max Act: 8.4016. Min Act: -0.1700
Data Index: 1064742 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4016. Min Range: -9.4016
Max Act: 8.4016. Min Act: -0.1700
Data Index: 2188753 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19