Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 512 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.5693. Min Act: -0.1700
Data Index: 1113445 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.2256. Min Act: -0.1700
Data Index: 5097916 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.2568. Min Act: -0.1700
Data Index: 8780795 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.1943. Min Act: -0.1700
Data Index: 1361842 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.0693. Min Act: -0.1700
Data Index: 8451860 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.0693. Min Act: -0.1700
Data Index: 1397010 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.0693. Min Act: -0.1700
Data Index: 4464709 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.0381. Min Act: -0.1700
Data Index: 3886822 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.0068. Min Act: -0.1700
Data Index: 6849530 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.0068. Min Act: -0.1700
Data Index: 4337828 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.0068. Min Act: -0.1700
Data Index: 3322088 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.0068. Min Act: -0.1700
Data Index: 257140 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5693. Min Range: -6.5693
Max Act: 5.9756. Min Act: -0.1700
Data Index: 7723402 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5693. Min Range: -6.5693
Max Act: 5.9756. Min Act: -0.1700
Data Index: 968097 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5693. Min Range: -6.5693
Max Act: 5.9756. Min Act: -0.1700
Data Index: 4201594 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5693. Min Range: -6.5693
Max Act: 5.9443. Min Act: -0.1700
Data Index: 3839599 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5693. Min Range: -6.5693
Max Act: 5.9443. Min Act: -0.1700
Data Index: 6739237 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5693. Min Range: -6.5693
Max Act: 5.9443. Min Act: -0.1700
Data Index: 816644 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5693. Min Range: -6.5693
Max Act: 5.9131. Min Act: -0.1700
Data Index: 2565566 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5693. Min Range: -6.5693
Max Act: 5.8506. Min Act: -0.1700
Data Index: 2433602 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19