Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5772 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7869. Min Range: -4.7869
Max Act: 4.7869. Min Act: -0.1700
Data Index: 4898295 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7869. Min Range: -4.7869
Max Act: 4.7557. Min Act: -0.1700
Data Index: 7107935 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7869. Min Range: -4.7869
Max Act: 4.6932. Min Act: -0.1700
Data Index: 7555235 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7869. Min Range: -4.7869
Max Act: 4.7244. Min Act: -0.1700
Data Index: 7969782 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7869. Min Range: -4.7869
Max Act: 4.7244. Min Act: -0.1700
Data Index: 8694616 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7869. Min Range: -4.7869
Max Act: 4.6932. Min Act: -0.1700
Data Index: 6644776 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7869. Min Range: -4.7869
Max Act: 4.6932. Min Act: -0.1700
Data Index: 865118 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7869. Min Range: -4.7869
Max Act: 4.6932. Min Act: -0.1700
Data Index: 988180 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7869. Min Range: -4.7869
Max Act: 4.6932. Min Act: -0.1700
Data Index: 5662348 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7869. Min Range: -4.7869
Max Act: 4.6932. Min Act: -0.1700
Data Index: 1361133 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7869. Min Range: -4.7869
Max Act: 4.6932. Min Act: -0.1700
Data Index: 8414629 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7869. Min Range: -4.7869
Max Act: 4.6932. Min Act: -0.1700
Data Index: 8166285 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7869. Min Range: -4.7869
Max Act: 4.6932. Min Act: -0.1700
Data Index: 2434757 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7869. Min Range: -4.7869
Max Act: 4.6932. Min Act: -0.1700
Data Index: 3029784 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7869. Min Range: -4.7869
Max Act: 4.6619. Min Act: -0.1700
Data Index: 4342818 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7869. Min Range: -4.7869
Max Act: 4.6619. Min Act: -0.1700
Data Index: 5104060 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7869. Min Range: -4.7869
Max Act: 4.6619. Min Act: -0.1700
Data Index: 931114 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7869. Min Range: -4.7869
Max Act: 4.6619. Min Act: -0.1700
Data Index: 5828485 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7869. Min Range: -4.7869
Max Act: 4.6619. Min Act: -0.1700
Data Index: 1424377 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7869. Min Range: -4.7869
Max Act: 4.6619. Min Act: -0.1700
Data Index: 6438648 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19