Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5404 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5052. Min Range: -5.5052
Max Act: 5.5052. Min Act: -0.1700
Data Index: 3691952 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5052. Min Range: -5.5052
Max Act: 5.3802. Min Act: -0.1700
Data Index: 4551594 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5052. Min Range: -5.5052
Max Act: 5.3177. Min Act: -0.1700
Data Index: 5162877 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5052. Min Range: -5.5052
Max Act: 5.2865. Min Act: -0.1700
Data Index: 7494410 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5052. Min Range: -5.5052
Max Act: 5.2552. Min Act: -0.1700
Data Index: 6101537 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5052. Min Range: -5.5052
Max Act: 5.2552. Min Act: -0.1700
Data Index: 2146345 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5052. Min Range: -5.5052
Max Act: 5.2552. Min Act: -0.1700
Data Index: 7678197 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5052. Min Range: -5.5052
Max Act: 5.1927. Min Act: -0.1700
Data Index: 1321050 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5052. Min Range: -5.5052
Max Act: 5.1615. Min Act: -0.1700
Data Index: 141894 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5052. Min Range: -5.5052
Max Act: 5.1615. Min Act: -0.1700
Data Index: 6868191 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5052. Min Range: -5.5052
Max Act: 5.1302. Min Act: -0.1700
Data Index: 6763900 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5052. Min Range: -5.5052
Max Act: 5.0990. Min Act: -0.1700
Data Index: 5381290 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5052. Min Range: -5.5052
Max Act: 5.0990. Min Act: -0.1700
Data Index: 5928930 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5052. Min Range: -5.5052
Max Act: 5.0677. Min Act: -0.1700
Data Index: 6504942 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5052. Min Range: -5.5052
Max Act: 5.0677. Min Act: -0.1700
Data Index: 1064882 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5052. Min Range: -5.5052
Max Act: 5.0365. Min Act: -0.1700
Data Index: 8362142 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5052. Min Range: -5.5052
Max Act: 5.0365. Min Act: -0.1700
Data Index: 7551958 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5052. Min Range: -5.5052
Max Act: 5.0365. Min Act: -0.1700
Data Index: 6993781 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5052. Min Range: -5.5052
Max Act: 4.9740. Min Act: -0.1700
Data Index: 2474666 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5052. Min Range: -5.5052
Max Act: 5.0365. Min Act: -0.1700
Data Index: 713511 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19