Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4270 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1942. Min Range: -6.1942
Max Act: 6.1942. Min Act: -0.1700
Data Index: 8760532 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1942. Min Range: -6.1942
Max Act: 6.1942. Min Act: -0.1700
Data Index: 2702747 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1942. Min Range: -6.1942
Max Act: 6.1942. Min Act: -0.1700
Data Index: 5449186 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1942. Min Range: -6.1942
Max Act: 6.1629. Min Act: -0.1700
Data Index: 5956303 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1942. Min Range: -6.1942
Max Act: 6.1004. Min Act: -0.1699
Data Index: 765022 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1942. Min Range: -6.1942
Max Act: 6.1317. Min Act: -0.1700
Data Index: 8146798 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1942. Min Range: -6.1942
Max Act: 6.0692. Min Act: -0.1700
Data Index: 3750936 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1942. Min Range: -6.1942
Max Act: 6.0692. Min Act: -0.1700
Data Index: 8389072 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1942. Min Range: -6.1942
Max Act: 6.0379. Min Act: -0.1700
Data Index: 7485603 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1942. Min Range: -6.1942
Max Act: 6.0067. Min Act: -0.1700
Data Index: 7270012 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1942. Min Range: -6.1942
Max Act: 5.9754. Min Act: -0.1700
Data Index: 1595214 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1942. Min Range: -6.1942
Max Act: 5.9754. Min Act: -0.1700
Data Index: 4723819 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1942. Min Range: -6.1942
Max Act: 5.9754. Min Act: -0.1700
Data Index: 5253641 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1942. Min Range: -6.1942
Max Act: 5.9754. Min Act: -0.1700
Data Index: 661276 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1942. Min Range: -6.1942
Max Act: 5.9442. Min Act: -0.1700
Data Index: 4493404 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1942. Min Range: -6.1942
Max Act: 5.9442. Min Act: -0.1700
Data Index: 7301870 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1942. Min Range: -6.1942
Max Act: 5.9442. Min Act: -0.1700
Data Index: 1118423 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1942. Min Range: -6.1942
Max Act: 5.9129. Min Act: -0.1700
Data Index: 1996672 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1942. Min Range: -6.1942
Max Act: 5.9129. Min Act: -0.1700
Data Index: 7947845 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1942. Min Range: -6.1942
Max Act: 5.9129. Min Act: -0.1700
Data Index: 4285979 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19