Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5255 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1624. Min Range: -11.1624
Max Act: 11.1624. Min Act: -0.1700
Data Index: 1217228 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1624. Min Range: -11.1624
Max Act: 10.7874. Min Act: -0.1700
Data Index: 5929423 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1624. Min Range: -11.1624
Max Act: 10.5374. Min Act: -0.1700
Data Index: 2175117 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1624. Min Range: -11.1624
Max Act: 10.4749. Min Act: -0.1700
Data Index: 6374369 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1624. Min Range: -11.1624
Max Act: 10.4124. Min Act: -0.1700
Data Index: 533438 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1624. Min Range: -11.1624
Max Act: 10.3499. Min Act: -0.1700
Data Index: 7628183 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1624. Min Range: -11.1624
Max Act: 10.0999. Min Act: -0.1700
Data Index: 4002395 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1624. Min Range: -11.1624
Max Act: 10.0999. Min Act: -0.1700
Data Index: 4903104 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1624. Min Range: -11.1624
Max Act: 10.0374. Min Act: -0.1700
Data Index: 2178941 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1624. Min Range: -11.1624
Max Act: 9.9749. Min Act: -0.1700
Data Index: 4914273 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1624. Min Range: -11.1624
Max Act: 9.9749. Min Act: -0.1700
Data Index: 3345027 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1624. Min Range: -11.1624
Max Act: 9.9124. Min Act: -0.1700
Data Index: 4097086 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1624. Min Range: -11.1624
Max Act: 9.9124. Min Act: -0.1700
Data Index: 795613 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1624. Min Range: -11.1624
Max Act: 9.9124. Min Act: -0.1700
Data Index: 2231098 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1624. Min Range: -11.1624
Max Act: 9.9124. Min Act: -0.1700
Data Index: 903212 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1624. Min Range: -11.1624
Max Act: 9.7874. Min Act: -0.1700
Data Index: 8655086 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1624. Min Range: -11.1624
Max Act: 9.8499. Min Act: -0.1700
Data Index: 2700083 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1624. Min Range: -11.1624
Max Act: 9.7874. Min Act: -0.1700
Data Index: 6117230 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1624. Min Range: -11.1624
Max Act: 9.7874. Min Act: -0.1700
Data Index: 5149228 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1624. Min Range: -11.1624
Max Act: 9.7874. Min Act: -0.1700
Data Index: 1698044 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19