Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2050 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9061. Min Range: -8.9061
Max Act: 8.8436. Min Act: -0.1700
Data Index: 7052524 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9061. Min Range: -8.9061
Max Act: 8.9061. Min Act: -0.1700
Data Index: 2013554 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9061. Min Range: -8.9061
Max Act: 8.6561. Min Act: -0.1700
Data Index: 3371939 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9061. Min Range: -8.9061
Max Act: 8.4999. Min Act: -0.1700
Data Index: 6285925 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9061. Min Range: -8.9061
Max Act: 8.3436. Min Act: -0.1700
Data Index: 5055156 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9061. Min Range: -8.9061
Max Act: 8.3436. Min Act: -0.1700
Data Index: 4725765 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9061. Min Range: -8.9061
Max Act: 8.3124. Min Act: -0.1700
Data Index: 4256911 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9061. Min Range: -8.9061
Max Act: 8.1249. Min Act: -0.1700
Data Index: 5055154 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9061. Min Range: -8.9061
Max Act: 8.1561. Min Act: -0.1700
Data Index: 4040209 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9061. Min Range: -8.9061
Max Act: 8.1249. Min Act: -0.1700
Data Index: 8138104 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9061. Min Range: -8.9061
Max Act: 8.0311. Min Act: -0.1700
Data Index: 2321978 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9061. Min Range: -8.9061
Max Act: 7.8749. Min Act: -0.1700
Data Index: 5535368 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9061. Min Range: -8.9061
Max Act: 7.7811. Min Act: -0.1700
Data Index: 2931283 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9061. Min Range: -8.9061
Max Act: 7.8124. Min Act: -0.1700
Data Index: 8107260 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9061. Min Range: -8.9061
Max Act: 7.8124. Min Act: -0.1700
Data Index: 5737187 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9061. Min Range: -8.9061
Max Act: 7.7499. Min Act: -0.1700
Data Index: 1573461 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9061. Min Range: -8.9061
Max Act: 7.7499. Min Act: -0.1700
Data Index: 3371938 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9061. Min Range: -8.9061
Max Act: 7.6874. Min Act: -0.1700
Data Index: 5475540 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9061. Min Range: -8.9061
Max Act: 7.6249. Min Act: -0.1700
Data Index: 3573316 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9061. Min Range: -8.9061
Max Act: 7.6874. Min Act: -0.1700
Data Index: 908842 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19