Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3407 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0039. Min Range: -5.0039
Max Act: 5.0039. Min Act: -0.1700
Data Index: 169989 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0039. Min Range: -5.0039
Max Act: 4.9414. Min Act: -0.1700
Data Index: 6401859 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0039. Min Range: -5.0039
Max Act: 4.9726. Min Act: -0.1700
Data Index: 4282022 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0039. Min Range: -5.0039
Max Act: 4.9101. Min Act: -0.1700
Data Index: 4786916 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0039. Min Range: -5.0039
Max Act: 4.8789. Min Act: -0.1700
Data Index: 5457373 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0039. Min Range: -5.0039
Max Act: 4.8476. Min Act: -0.1700
Data Index: 7956607 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0039. Min Range: -5.0039
Max Act: 4.8476. Min Act: -0.1700
Data Index: 7303917 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0039. Min Range: -5.0039
Max Act: 4.8164. Min Act: -0.1700
Data Index: 6290908 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0039. Min Range: -5.0039
Max Act: 4.8164. Min Act: -0.1700
Data Index: 4235265 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0039. Min Range: -5.0039
Max Act: 4.8164. Min Act: -0.1700
Data Index: 4658303 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0039. Min Range: -5.0039
Max Act: 4.8476. Min Act: -0.1700
Data Index: 3111254 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0039. Min Range: -5.0039
Max Act: 4.7851. Min Act: -0.1700
Data Index: 6311249 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0039. Min Range: -5.0039
Max Act: 4.7851. Min Act: -0.1700
Data Index: 2445097 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0039. Min Range: -5.0039
Max Act: 4.7226. Min Act: -0.1700
Data Index: 3635138 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0039. Min Range: -5.0039
Max Act: 4.7539. Min Act: -0.1700
Data Index: 8448113 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0039. Min Range: -5.0039
Max Act: 4.7539. Min Act: -0.1700
Data Index: 2408688 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0039. Min Range: -5.0039
Max Act: 4.7539. Min Act: -0.1700
Data Index: 256326 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0039. Min Range: -5.0039
Max Act: 4.7226. Min Act: -0.1700
Data Index: 1897145 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0039. Min Range: -5.0039
Max Act: 4.7226. Min Act: -0.1700
Data Index: 4378596 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0039. Min Range: -5.0039
Max Act: 4.7226. Min Act: -0.1700
Data Index: 2627070 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19