Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4348 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8279. Min Range: -4.8279
Max Act: 4.8279. Min Act: -0.1700
Data Index: 1962705 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8279. Min Range: -4.8279
Max Act: 4.6717. Min Act: -0.1700
Data Index: 4239895 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8279. Min Range: -4.8279
Max Act: 4.6717. Min Act: -0.1700
Data Index: 6004274 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8279. Min Range: -4.8279
Max Act: 4.6717. Min Act: -0.1700
Data Index: 5567392 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8279. Min Range: -4.8279
Max Act: 4.6404. Min Act: -0.1700
Data Index: 1649194 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8279. Min Range: -4.8279
Max Act: 4.5779. Min Act: -0.1700
Data Index: 1950999 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8279. Min Range: -4.8279
Max Act: 4.5779. Min Act: -0.1700
Data Index: 4456988 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8279. Min Range: -4.8279
Max Act: 4.5779. Min Act: -0.1700
Data Index: 217551 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8279. Min Range: -4.8279
Max Act: 4.5779. Min Act: -0.1700
Data Index: 1649191 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8279. Min Range: -4.8279
Max Act: 4.5467. Min Act: -0.1700
Data Index: 5159403 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8279. Min Range: -4.8279
Max Act: 4.5467. Min Act: -0.1700
Data Index: 4674721 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8279. Min Range: -4.8279
Max Act: 4.5779. Min Act: -0.1700
Data Index: 38849 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8279. Min Range: -4.8279
Max Act: 4.5467. Min Act: -0.1700
Data Index: 3064155 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8279. Min Range: -4.8279
Max Act: 4.4842. Min Act: -0.1700
Data Index: 334302 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8279. Min Range: -4.8279
Max Act: 4.5154. Min Act: -0.1700
Data Index: 4662920 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8279. Min Range: -4.8279
Max Act: 4.5154. Min Act: -0.1700
Data Index: 5300551 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8279. Min Range: -4.8279
Max Act: 4.5154. Min Act: -0.1700
Data Index: 46978 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8279. Min Range: -4.8279
Max Act: 4.4842. Min Act: -0.1700
Data Index: 6893927 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8279. Min Range: -4.8279
Max Act: 4.4842. Min Act: -0.1700
Data Index: 1785217 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8279. Min Range: -4.8279
Max Act: 4.4529. Min Act: -0.1700
Data Index: 456605 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19