Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1047 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.5216. Min Act: -0.1700
Data Index: 8665069 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.4904. Min Act: -0.1700
Data Index: 8579740 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.4591. Min Act: -0.1700
Data Index: 8097526 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.3654. Min Act: -0.1700
Data Index: 6349403 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.4279. Min Act: -0.1700
Data Index: 5266878 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.3654. Min Act: -0.1700
Data Index: 8568999 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.3028. Min Act: -0.1700
Data Index: 711732 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.3028. Min Act: -0.1700
Data Index: 8594249 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.3341. Min Act: -0.1700
Data Index: 7661123 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.2716. Min Act: -0.1700
Data Index: 1285591 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.2716. Min Act: -0.1700
Data Index: 268840 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.2403. Min Act: -0.1700
Data Index: 4212192 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.2716. Min Act: -0.1700
Data Index: 5882570 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.2403. Min Act: -0.1700
Data Index: 2434033 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.2403. Min Act: -0.1700
Data Index: 8176386 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.2403. Min Act: -0.1700
Data Index: 2762232 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.2091. Min Act: -0.1700
Data Index: 8559970 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.1778. Min Act: -0.1700
Data Index: 6263559 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.2091. Min Act: -0.1700
Data Index: 6064270 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5216. Min Range: -4.5216
Max Act: 4.2091. Min Act: -0.1700
Data Index: 3461746 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19