Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3613 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2570. Min Range: -8.2570
Max Act: 8.2570. Min Act: -0.1700
Data Index: 2660907 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2570. Min Range: -8.2570
Max Act: 8.0070. Min Act: -0.1700
Data Index: 8399989 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2570. Min Range: -8.2570
Max Act: 7.8820. Min Act: -0.1700
Data Index: 6985817 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2570. Min Range: -8.2570
Max Act: 7.7882. Min Act: -0.1700
Data Index: 337404 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2570. Min Range: -8.2570
Max Act: 7.8195. Min Act: -0.1700
Data Index: 6095397 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2570. Min Range: -8.2570
Max Act: 7.8195. Min Act: -0.1700
Data Index: 5340721 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2570. Min Range: -8.2570
Max Act: 7.7882. Min Act: -0.1700
Data Index: 8647741 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2570. Min Range: -8.2570
Max Act: 7.7882. Min Act: -0.1700
Data Index: 6096698 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2570. Min Range: -8.2570
Max Act: 7.7570. Min Act: -0.1700
Data Index: 7965665 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2570. Min Range: -8.2570
Max Act: 7.7570. Min Act: -0.1700
Data Index: 7333875 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2570. Min Range: -8.2570
Max Act: 7.7570. Min Act: -0.1700
Data Index: 6674905 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2570. Min Range: -8.2570
Max Act: 7.7257. Min Act: -0.1700
Data Index: 3869019 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2570. Min Range: -8.2570
Max Act: 7.6632. Min Act: -0.1700
Data Index: 7244319 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2570. Min Range: -8.2570
Max Act: 7.6945. Min Act: -0.1700
Data Index: 114278 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2570. Min Range: -8.2570
Max Act: 7.6632. Min Act: -0.1700
Data Index: 3247287 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2570. Min Range: -8.2570
Max Act: 7.6632. Min Act: -0.1700
Data Index: 4019290 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2570. Min Range: -8.2570
Max Act: 7.6632. Min Act: -0.1700
Data Index: 952755 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2570. Min Range: -8.2570
Max Act: 7.6632. Min Act: -0.1700
Data Index: 6356923 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2570. Min Range: -8.2570
Max Act: 7.6320. Min Act: -0.1700
Data Index: 3554377 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2570. Min Range: -8.2570
Max Act: 7.6320. Min Act: -0.1700
Data Index: 1743273 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19