Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4332 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3298. Min Range: -6.3298
Max Act: 6.3298. Min Act: -0.1700
Data Index: 1596850 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3298. Min Range: -6.3298
Max Act: 6.2360. Min Act: -0.1700
Data Index: 1547392 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3298. Min Range: -6.3298
Max Act: 6.2048. Min Act: -0.1700
Data Index: 7665601 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3298. Min Range: -6.3298
Max Act: 6.0485. Min Act: -0.1700
Data Index: 8742370 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3298. Min Range: -6.3298
Max Act: 6.0173. Min Act: -0.1700
Data Index: 4023592 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3298. Min Range: -6.3298
Max Act: 5.9860. Min Act: -0.1700
Data Index: 1214955 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3298. Min Range: -6.3298
Max Act: 5.9548. Min Act: -0.1700
Data Index: 419271 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3298. Min Range: -6.3298
Max Act: 5.9548. Min Act: -0.1700
Data Index: 4331625 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3298. Min Range: -6.3298
Max Act: 5.9235. Min Act: -0.1700
Data Index: 2834825 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3298. Min Range: -6.3298
Max Act: 5.9235. Min Act: -0.1700
Data Index: 7085159 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3298. Min Range: -6.3298
Max Act: 5.8923. Min Act: -0.1700
Data Index: 3229425 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3298. Min Range: -6.3298
Max Act: 5.8923. Min Act: -0.1700
Data Index: 515370 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3298. Min Range: -6.3298
Max Act: 5.8923. Min Act: -0.1700
Data Index: 4593680 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3298. Min Range: -6.3298
Max Act: 5.8610. Min Act: -0.1700
Data Index: 3490362 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3298. Min Range: -6.3298
Max Act: 5.8610. Min Act: -0.1700
Data Index: 4646667 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3298. Min Range: -6.3298
Max Act: 5.8610. Min Act: -0.1700
Data Index: 1212960 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3298. Min Range: -6.3298
Max Act: 5.8610. Min Act: -0.1700
Data Index: 5242192 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3298. Min Range: -6.3298
Max Act: 5.8610. Min Act: -0.1700
Data Index: 3136939 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3298. Min Range: -6.3298
Max Act: 5.8298. Min Act: -0.1700
Data Index: 2602296 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3298. Min Range: -6.3298
Max Act: 5.8298. Min Act: -0.1700
Data Index: 2794151 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19