Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3592 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.3135. Min Act: -0.1700
Data Index: 8643862 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.2510. Min Act: -0.1700
Data Index: 2238650 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.1885. Min Act: -0.1700
Data Index: 6657798 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.1260. Min Act: -0.1700
Data Index: 8164303 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.0635. Min Act: -0.1700
Data Index: 4865826 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.0635. Min Act: -0.1700
Data Index: 5693650 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.0635. Min Act: -0.1700
Data Index: 6658075 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.0010. Min Act: -0.1700
Data Index: 4233180 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.0010. Min Act: -0.1700
Data Index: 6848276 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.0010. Min Act: -0.1700
Data Index: 2903632 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.0010. Min Act: -0.1700
Data Index: 8659166 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.0010. Min Act: -0.1700
Data Index: 6992977 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.0010. Min Act: -0.1700
Data Index: 3508148 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.0010. Min Act: -0.1700
Data Index: 6897512 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.0010. Min Act: -0.1700
Data Index: 2628447 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3135. Min Range: -8.3135
Max Act: 7.9385. Min Act: -0.1700
Data Index: 4328783 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3135. Min Range: -8.3135
Max Act: 7.9385. Min Act: -0.1700
Data Index: 1436079 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3135. Min Range: -8.3135
Max Act: 7.9385. Min Act: -0.1700
Data Index: 5570587 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3135. Min Range: -8.3135
Max Act: 7.9385. Min Act: -0.1700
Data Index: 4814058 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3135. Min Range: -8.3135
Max Act: 7.9385. Min Act: -0.1700
Data Index: 7623554 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19