Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 988 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6392. Min Range: -6.6392
Max Act: 6.6392. Min Act: -0.1700
Data Index: 3957179 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6392. Min Range: -6.6392
Max Act: 6.5767. Min Act: -0.1700
Data Index: 6650264 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6392. Min Range: -6.6392
Max Act: 6.4205. Min Act: -0.1700
Data Index: 3331831 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6392. Min Range: -6.6392
Max Act: 6.3892. Min Act: -0.1700
Data Index: 5713340 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6392. Min Range: -6.6392
Max Act: 6.3267. Min Act: -0.1700
Data Index: 4684945 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6392. Min Range: -6.6392
Max Act: 6.3580. Min Act: -0.1700
Data Index: 7465871 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6392. Min Range: -6.6392
Max Act: 6.3580. Min Act: -0.1700
Data Index: 666753 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6392. Min Range: -6.6392
Max Act: 6.2955. Min Act: -0.1700
Data Index: 5731083 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6392. Min Range: -6.6392
Max Act: 6.2330. Min Act: -0.1700
Data Index: 3360285 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6392. Min Range: -6.6392
Max Act: 6.2642. Min Act: -0.1700
Data Index: 1375151 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6392. Min Range: -6.6392
Max Act: 6.2330. Min Act: -0.1700
Data Index: 2526911 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6392. Min Range: -6.6392
Max Act: 6.2642. Min Act: -0.1700
Data Index: 4390149 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6392. Min Range: -6.6392
Max Act: 6.2017. Min Act: -0.1700
Data Index: 2178594 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6392. Min Range: -6.6392
Max Act: 6.1705. Min Act: -0.1700
Data Index: 5548670 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6392. Min Range: -6.6392
Max Act: 6.1705. Min Act: -0.1700
Data Index: 6242636 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6392. Min Range: -6.6392
Max Act: 6.1392. Min Act: -0.1700
Data Index: 1416583 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6392. Min Range: -6.6392
Max Act: 6.1392. Min Act: -0.1700
Data Index: 6971055 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6392. Min Range: -6.6392
Max Act: 6.0767. Min Act: -0.1700
Data Index: 2167653 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6392. Min Range: -6.6392
Max Act: 6.1392. Min Act: -0.1700
Data Index: 7060563 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6392. Min Range: -6.6392
Max Act: 6.1080. Min Act: -0.1700
Data Index: 4260328 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19