Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4192 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4555. Min Range: -6.4555
Max Act: 6.4555. Min Act: -0.1700
Data Index: 4908332 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4555. Min Range: -6.4555
Max Act: 6.2992. Min Act: -0.1700
Data Index: 5669716 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4555. Min Range: -6.4555
Max Act: 6.2680. Min Act: -0.1700
Data Index: 4765197 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4555. Min Range: -6.4555
Max Act: 6.2680. Min Act: -0.1700
Data Index: 1232245 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4555. Min Range: -6.4555
Max Act: 6.2367. Min Act: -0.1700
Data Index: 7402116 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4555. Min Range: -6.4555
Max Act: 6.1430. Min Act: -0.1700
Data Index: 101614 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4555. Min Range: -6.4555
Max Act: 6.1117. Min Act: -0.1700
Data Index: 5385962 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4555. Min Range: -6.4555
Max Act: 6.0805. Min Act: -0.1700
Data Index: 158952 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4555. Min Range: -6.4555
Max Act: 6.0805. Min Act: -0.1700
Data Index: 4247861 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4555. Min Range: -6.4555
Max Act: 6.0180. Min Act: -0.1700
Data Index: 3064429 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4555. Min Range: -6.4555
Max Act: 6.0492. Min Act: -0.1700
Data Index: 7187399 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4555. Min Range: -6.4555
Max Act: 6.0492. Min Act: -0.1700
Data Index: 3269867 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4555. Min Range: -6.4555
Max Act: 6.0492. Min Act: -0.1700
Data Index: 4475063 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4555. Min Range: -6.4555
Max Act: 6.0492. Min Act: -0.1700
Data Index: 7505980 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4555. Min Range: -6.4555
Max Act: 6.0180. Min Act: -0.1700
Data Index: 7202038 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4555. Min Range: -6.4555
Max Act: 6.0492. Min Act: -0.1700
Data Index: 4413247 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4555. Min Range: -6.4555
Max Act: 6.0180. Min Act: -0.1700
Data Index: 2473012 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4555. Min Range: -6.4555
Max Act: 5.9867. Min Act: -0.1700
Data Index: 2290778 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4555. Min Range: -6.4555
Max Act: 5.9555. Min Act: -0.1700
Data Index: 3574069 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4555. Min Range: -6.4555
Max Act: 5.9242. Min Act: -0.1700
Data Index: 3947061 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19