Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1285 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0978. Min Range: -5.0978
Max Act: 5.0978. Min Act: -0.1700
Data Index: 1166503 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0978. Min Range: -5.0978
Max Act: 5.0665. Min Act: -0.1700
Data Index: 1902031 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.7540. Min Act: -0.1700
Data Index: 7299092 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.6290. Min Act: -0.1700
Data Index: 3467340 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.5978. Min Act: -0.1700
Data Index: 7318695 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.5040. Min Act: -0.1700
Data Index: 4390749 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.4103. Min Act: -0.1700
Data Index: 377211 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.4103. Min Act: -0.1700
Data Index: 377210 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.3790. Min Act: -0.1700
Data Index: 2840518 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.3478. Min Act: -0.1700
Data Index: 4493669 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.3478. Min Act: -0.1700
Data Index: 2416110 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.3478. Min Act: -0.1700
Data Index: 2631579 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.3478. Min Act: -0.1700
Data Index: 7813318 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.3165. Min Act: -0.1700
Data Index: 1670129 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.1915. Min Act: -0.1700
Data Index: 6648670 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.2228. Min Act: -0.1700
Data Index: 1046860 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.2228. Min Act: -0.1700
Data Index: 5559650 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.2228. Min Act: -0.1700
Data Index: 7597294 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.1603. Min Act: -0.1700
Data Index: 1498489 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.1290. Min Act: -0.1700
Data Index: 2550596 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19