Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1679 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7942. Min Range: -4.7942
Max Act: 4.7942. Min Act: -0.1700
Data Index: 260265 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7942. Min Range: -4.7942
Max Act: 4.7630. Min Act: -0.1700
Data Index: 3501800 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7942. Min Range: -4.7942
Max Act: 4.7630. Min Act: -0.1700
Data Index: 5051634 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7942. Min Range: -4.7942
Max Act: 4.6692. Min Act: -0.1700
Data Index: 7629723 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7942. Min Range: -4.7942
Max Act: 4.7005. Min Act: -0.1700
Data Index: 3738214 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7942. Min Range: -4.7942
Max Act: 4.6692. Min Act: -0.1700
Data Index: 2028777 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7942. Min Range: -4.7942
Max Act: 4.6692. Min Act: -0.1700
Data Index: 739383 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7942. Min Range: -4.7942
Max Act: 4.6692. Min Act: -0.1700
Data Index: 617088 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7942. Min Range: -4.7942
Max Act: 4.6380. Min Act: -0.1700
Data Index: 695786 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7942. Min Range: -4.7942
Max Act: 4.6380. Min Act: -0.1700
Data Index: 3153386 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7942. Min Range: -4.7942
Max Act: 4.5755. Min Act: -0.1700
Data Index: 4582000 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7942. Min Range: -4.7942
Max Act: 4.5755. Min Act: -0.1700
Data Index: 4297031 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7942. Min Range: -4.7942
Max Act: 4.5442. Min Act: -0.1700
Data Index: 8430767 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7942. Min Range: -4.7942
Max Act: 4.5442. Min Act: -0.1700
Data Index: 3367968 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7942. Min Range: -4.7942
Max Act: 4.5442. Min Act: -0.1700
Data Index: 6603895 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7942. Min Range: -4.7942
Max Act: 4.5130. Min Act: -0.1700
Data Index: 7822277 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7942. Min Range: -4.7942
Max Act: 4.5130. Min Act: -0.1700
Data Index: 3245287 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7942. Min Range: -4.7942
Max Act: 4.5442. Min Act: -0.1700
Data Index: 7491170 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7942. Min Range: -4.7942
Max Act: 4.5130. Min Act: -0.1700
Data Index: 692684 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7942. Min Range: -4.7942
Max Act: 4.5130. Min Act: -0.1700
Data Index: 5450101 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19