Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1622 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.5942. Min Act: -0.1700
Data Index: 1552548 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.5317. Min Act: -0.1700
Data Index: 6775440 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.5317. Min Act: -0.1700
Data Index: 6209126 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.4379. Min Act: -0.1700
Data Index: 6718870 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.3754. Min Act: -0.1700
Data Index: 3347166 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.3442. Min Act: -0.1700
Data Index: 5934726 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.3129. Min Act: -0.1700
Data Index: 2672347 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.3129. Min Act: -0.1700
Data Index: 2475284 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.2817. Min Act: -0.1700
Data Index: 7058224 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.2817. Min Act: -0.1700
Data Index: 4620461 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.2817. Min Act: -0.1700
Data Index: 8338553 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.2504. Min Act: -0.1700
Data Index: 8038266 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.2817. Min Act: -0.1700
Data Index: 7545749 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.2504. Min Act: -0.1700
Data Index: 813978 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.2192. Min Act: -0.1700
Data Index: 1286999 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.2192. Min Act: -0.1700
Data Index: 3677038 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.2192. Min Act: -0.1700
Data Index: 5081884 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.2192. Min Act: -0.1700
Data Index: 565645 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.1879. Min Act: -0.1700
Data Index: 3347299 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.2192. Min Act: -0.1700
Data Index: 5078176 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19