Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4470 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4510. Min Range: -5.4510
Max Act: 5.4510. Min Act: -0.1700
Data Index: 5829861 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4510. Min Range: -5.4510
Max Act: 5.3885. Min Act: -0.1700
Data Index: 6715877 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4510. Min Range: -5.4510
Max Act: 5.3573. Min Act: -0.1700
Data Index: 4999019 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4510. Min Range: -5.4510
Max Act: 5.3573. Min Act: -0.1700
Data Index: 8205874 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4510. Min Range: -5.4510
Max Act: 5.3260. Min Act: -0.1700
Data Index: 4706576 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4510. Min Range: -5.4510
Max Act: 5.3260. Min Act: -0.1700
Data Index: 2313101 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4510. Min Range: -5.4510
Max Act: 5.2948. Min Act: -0.1700
Data Index: 6051610 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4510. Min Range: -5.4510
Max Act: 5.2948. Min Act: -0.1700
Data Index: 4386330 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4510. Min Range: -5.4510
Max Act: 5.2948. Min Act: -0.1700
Data Index: 5755649 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4510. Min Range: -5.4510
Max Act: 5.2948. Min Act: -0.1700
Data Index: 489067 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4510. Min Range: -5.4510
Max Act: 5.2635. Min Act: -0.1700
Data Index: 349775 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4510. Min Range: -5.4510
Max Act: 5.2948. Min Act: -0.1700
Data Index: 2347233 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4510. Min Range: -5.4510
Max Act: 5.2323. Min Act: -0.1700
Data Index: 7923933 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4510. Min Range: -5.4510
Max Act: 5.2323. Min Act: -0.1700
Data Index: 3742964 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4510. Min Range: -5.4510
Max Act: 5.2323. Min Act: -0.1700
Data Index: 2293919 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4510. Min Range: -5.4510
Max Act: 5.2323. Min Act: -0.1700
Data Index: 7074135 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4510. Min Range: -5.4510
Max Act: 5.2323. Min Act: -0.1700
Data Index: 2977282 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4510. Min Range: -5.4510
Max Act: 5.2010. Min Act: -0.1700
Data Index: 7617351 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4510. Min Range: -5.4510
Max Act: 5.2010. Min Act: -0.1700
Data Index: 3724861 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4510. Min Range: -5.4510
Max Act: 5.2010. Min Act: -0.1700
Data Index: 7083088 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19