Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5858 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5554. Min Range: -5.5554
Max Act: 5.5554. Min Act: -0.1700
Data Index: 8473282 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5554. Min Range: -5.5554
Max Act: 5.4616. Min Act: -0.1700
Data Index: 3590412 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5554. Min Range: -5.5554
Max Act: 5.3679. Min Act: -0.1700
Data Index: 3949275 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5554. Min Range: -5.5554
Max Act: 5.3054. Min Act: -0.1700
Data Index: 5234882 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5554. Min Range: -5.5554
Max Act: 5.1804. Min Act: -0.1700
Data Index: 4215888 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5554. Min Range: -5.5554
Max Act: 5.1179. Min Act: -0.1700
Data Index: 5335104 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5554. Min Range: -5.5554
Max Act: 5.1491. Min Act: -0.1700
Data Index: 8327330 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5554. Min Range: -5.5554
Max Act: 5.1491. Min Act: -0.1700
Data Index: 2475963 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5554. Min Range: -5.5554
Max Act: 5.1179. Min Act: -0.1700
Data Index: 7592510 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5554. Min Range: -5.5554
Max Act: 5.1179. Min Act: -0.1700
Data Index: 3639232 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5554. Min Range: -5.5554
Max Act: 5.1179. Min Act: -0.1700
Data Index: 6309875 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5554. Min Range: -5.5554
Max Act: 5.0866. Min Act: -0.1700
Data Index: 2129344 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5554. Min Range: -5.5554
Max Act: 5.0554. Min Act: -0.1700
Data Index: 7365597 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5554. Min Range: -5.5554
Max Act: 5.0866. Min Act: -0.1700
Data Index: 7982589 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5554. Min Range: -5.5554
Max Act: 5.0866. Min Act: -0.1700
Data Index: 6156678 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5554. Min Range: -5.5554
Max Act: 5.0866. Min Act: -0.1700
Data Index: 3635134 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5554. Min Range: -5.5554
Max Act: 5.0866. Min Act: -0.1700
Data Index: 5378182 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5554. Min Range: -5.5554
Max Act: 5.0554. Min Act: -0.1700
Data Index: 3614687 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5554. Min Range: -5.5554
Max Act: 5.0554. Min Act: -0.1700
Data Index: 1824175 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5554. Min Range: -5.5554
Max Act: 5.0554. Min Act: -0.1700
Data Index: 2398787 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19