Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3388 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1076. Min Range: -6.1076
Max Act: 6.1076. Min Act: -0.1700
Data Index: 4538442 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.3888. Min Act: -0.1700
Data Index: 3125312 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.2013. Min Act: -0.1700
Data Index: 5859782 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.2013. Min Act: -0.1700
Data Index: 8625433 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.2326. Min Act: -0.1700
Data Index: 1780486 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.2013. Min Act: -0.1700
Data Index: 7148245 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.1076. Min Act: -0.1700
Data Index: 573841 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.1076. Min Act: -0.1700
Data Index: 36303 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.1076. Min Act: -0.1700
Data Index: 3644590 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.0763. Min Act: -0.1700
Data Index: 7409224 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.0451. Min Act: -0.1700
Data Index: 7728876 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1076. Min Range: -6.1076
Max Act: 4.9826. Min Act: -0.1700
Data Index: 1780477 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.0138. Min Act: -0.1700
Data Index: 1526233 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.0138. Min Act: -0.1700
Data Index: 643403 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1076. Min Range: -6.1076
Max Act: 4.9826. Min Act: -0.1700
Data Index: 2500064 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1076. Min Range: -6.1076
Max Act: 4.9826. Min Act: -0.1700
Data Index: 4727266 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1076. Min Range: -6.1076
Max Act: 4.9826. Min Act: -0.1700
Data Index: 465406 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1076. Min Range: -6.1076
Max Act: 4.9513. Min Act: -0.1700
Data Index: 779721 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1076. Min Range: -6.1076
Max Act: 4.9513. Min Act: -0.1700
Data Index: 905741 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1076. Min Range: -6.1076
Max Act: 4.9201. Min Act: -0.1700
Data Index: 5160533 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19