Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5866 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0545. Min Range: -9.0545
Max Act: 9.0545. Min Act: -0.1700
Data Index: 1718302 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0545. Min Range: -9.0545
Max Act: 8.9920. Min Act: -0.1700
Data Index: 3186983 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0545. Min Range: -9.0545
Max Act: 8.8045. Min Act: -0.1700
Data Index: 4125208 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0545. Min Range: -9.0545
Max Act: 8.6170. Min Act: -0.1700
Data Index: 4456909 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0545. Min Range: -9.0545
Max Act: 8.6170. Min Act: -0.1700
Data Index: 4280105 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0545. Min Range: -9.0545
Max Act: 8.6170. Min Act: -0.1700
Data Index: 3584997 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0545. Min Range: -9.0545
Max Act: 8.6170. Min Act: -0.1700
Data Index: 5659965 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0545. Min Range: -9.0545
Max Act: 8.4920. Min Act: -0.1700
Data Index: 106255 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0545. Min Range: -9.0545
Max Act: 8.5545. Min Act: -0.1700
Data Index: 7742009 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0545. Min Range: -9.0545
Max Act: 8.5545. Min Act: -0.1700
Data Index: 3335514 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0545. Min Range: -9.0545
Max Act: 8.4920. Min Act: -0.1700
Data Index: 14788 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0545. Min Range: -9.0545
Max Act: 8.5545. Min Act: -0.1700
Data Index: 5931859 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0545. Min Range: -9.0545
Max Act: 8.4920. Min Act: -0.1700
Data Index: 933660 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0545. Min Range: -9.0545
Max Act: 8.4920. Min Act: -0.1700
Data Index: 123086 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0545. Min Range: -9.0545
Max Act: 8.4295. Min Act: -0.1700
Data Index: 45132 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0545. Min Range: -9.0545
Max Act: 8.4295. Min Act: -0.1700
Data Index: 8628254 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0545. Min Range: -9.0545
Max Act: 8.3670. Min Act: -0.1700
Data Index: 2751922 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0545. Min Range: -9.0545
Max Act: 8.4295. Min Act: -0.1700
Data Index: 6335355 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0545. Min Range: -9.0545
Max Act: 8.4295. Min Act: -0.1700
Data Index: 3488111 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0545. Min Range: -9.0545
Max Act: 8.3670. Min Act: -0.1700
Data Index: 3584998 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19