Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3163 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0705. Min Range: -5.0705
Max Act: 5.0705. Min Act: -0.1700
Data Index: 2812515 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0705. Min Range: -5.0705
Max Act: 5.0080. Min Act: -0.1700
Data Index: 4150744 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.8830. Min Act: -0.1700
Data Index: 5937417 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.8517. Min Act: -0.1700
Data Index: 6986734 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.8205. Min Act: -0.1700
Data Index: 4562174 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.7892. Min Act: -0.1700
Data Index: 1532127 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.7892. Min Act: -0.1700
Data Index: 7202189 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.7892. Min Act: -0.1700
Data Index: 7612318 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.7892. Min Act: -0.1700
Data Index: 3123112 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.7580. Min Act: -0.1700
Data Index: 6861153 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.7267. Min Act: -0.1700
Data Index: 8816987 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.7267. Min Act: -0.1700
Data Index: 3353995 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.6955. Min Act: -0.1700
Data Index: 3463580 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.6955. Min Act: -0.1700
Data Index: 2023501 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.7267. Min Act: -0.1700
Data Index: 5182713 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.6955. Min Act: -0.1700
Data Index: 997034 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.6642. Min Act: -0.1700
Data Index: 3295575 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.7267. Min Act: -0.1700
Data Index: 6041101 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.6642. Min Act: -0.1700
Data Index: 7997408 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.6642. Min Act: -0.1700
Data Index: 850531 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19