Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5990 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8574. Min Range: -5.8574
Max Act: 5.8574. Min Act: -0.1700
Data Index: 1085572 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8574. Min Range: -5.8574
Max Act: 5.8262. Min Act: -0.1700
Data Index: 2473518 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8574. Min Range: -5.8574
Max Act: 5.8262. Min Act: -0.1700
Data Index: 6858998 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8574. Min Range: -5.8574
Max Act: 5.8262. Min Act: -0.1700
Data Index: 6711665 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8574. Min Range: -5.8574
Max Act: 5.7637. Min Act: -0.1700
Data Index: 3842740 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8574. Min Range: -5.8574
Max Act: 5.7637. Min Act: -0.1700
Data Index: 7226676 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8574. Min Range: -5.8574
Max Act: 5.6699. Min Act: -0.1700
Data Index: 236671 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8574. Min Range: -5.8574
Max Act: 5.6387. Min Act: -0.1700
Data Index: 2940931 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8574. Min Range: -5.8574
Max Act: 5.6074. Min Act: -0.1700
Data Index: 8231975 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8574. Min Range: -5.8574
Max Act: 5.6074. Min Act: -0.1700
Data Index: 4699408 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8574. Min Range: -5.8574
Max Act: 5.5762. Min Act: -0.1700
Data Index: 3821655 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8574. Min Range: -5.8574
Max Act: 5.5449. Min Act: -0.1700
Data Index: 5342429 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8574. Min Range: -5.8574
Max Act: 5.4824. Min Act: -0.1700
Data Index: 8235873 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8574. Min Range: -5.8574
Max Act: 5.4824. Min Act: -0.1700
Data Index: 458721 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8574. Min Range: -5.8574
Max Act: 5.4512. Min Act: -0.1700
Data Index: 338997 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8574. Min Range: -5.8574
Max Act: 5.4824. Min Act: -0.1700
Data Index: 3814210 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8574. Min Range: -5.8574
Max Act: 5.4199. Min Act: -0.1700
Data Index: 6902359 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8574. Min Range: -5.8574
Max Act: 5.4199. Min Act: -0.1700
Data Index: 707023 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8574. Min Range: -5.8574
Max Act: 5.4512. Min Act: -0.1700
Data Index: 5879924 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8574. Min Range: -5.8574
Max Act: 5.3887. Min Act: -0.1700
Data Index: 5145468 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19