Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4682 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9348. Min Range: -4.9348
Max Act: 4.9348. Min Act: -0.1700
Data Index: 2621923 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9348. Min Range: -4.9348
Max Act: 4.9035. Min Act: -0.1700
Data Index: 779890 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9348. Min Range: -4.9348
Max Act: 4.8723. Min Act: -0.1700
Data Index: 2758591 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9348. Min Range: -4.9348
Max Act: 4.8098. Min Act: -0.1700
Data Index: 2382529 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9348. Min Range: -4.9348
Max Act: 4.8098. Min Act: -0.1700
Data Index: 2885034 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9348. Min Range: -4.9348
Max Act: 4.7785. Min Act: -0.1700
Data Index: 5370540 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9348. Min Range: -4.9348
Max Act: 4.7473. Min Act: -0.1700
Data Index: 3793596 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9348. Min Range: -4.9348
Max Act: 4.7473. Min Act: -0.1700
Data Index: 6485045 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9348. Min Range: -4.9348
Max Act: 4.7473. Min Act: -0.1700
Data Index: 1918332 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9348. Min Range: -4.9348
Max Act: 4.7473. Min Act: -0.1700
Data Index: 5621147 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9348. Min Range: -4.9348
Max Act: 4.7160. Min Act: -0.1700
Data Index: 341189 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9348. Min Range: -4.9348
Max Act: 4.7160. Min Act: -0.1700
Data Index: 4809079 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9348. Min Range: -4.9348
Max Act: 4.7160. Min Act: -0.1700
Data Index: 1085951 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9348. Min Range: -4.9348
Max Act: 4.7160. Min Act: -0.1700
Data Index: 1801205 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9348. Min Range: -4.9348
Max Act: 4.6848. Min Act: -0.1700
Data Index: 4455957 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9348. Min Range: -4.9348
Max Act: 4.6848. Min Act: -0.1700
Data Index: 902890 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9348. Min Range: -4.9348
Max Act: 4.7160. Min Act: -0.1700
Data Index: 8000949 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9348. Min Range: -4.9348
Max Act: 4.6848. Min Act: -0.1700
Data Index: 8385741 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9348. Min Range: -4.9348
Max Act: 4.6848. Min Act: -0.1700
Data Index: 7093281 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9348. Min Range: -4.9348
Max Act: 4.6848. Min Act: -0.1700
Data Index: 5230902 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19