Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1988 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7968. Min Range: -5.7968
Max Act: 5.7968. Min Act: -0.1700
Data Index: 4364540 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7968. Min Range: -5.7968
Max Act: 5.3906. Min Act: -0.1700
Data Index: 2672751 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7968. Min Range: -5.7968
Max Act: 5.3281. Min Act: -0.1700
Data Index: 541876 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7968. Min Range: -5.7968
Max Act: 5.2343. Min Act: -0.1700
Data Index: 5630715 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7968. Min Range: -5.7968
Max Act: 5.2343. Min Act: -0.1700
Data Index: 3474603 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7968. Min Range: -5.7968
Max Act: 5.1718. Min Act: -0.1700
Data Index: 1920599 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7968. Min Range: -5.7968
Max Act: 5.1718. Min Act: -0.1700
Data Index: 535516 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7968. Min Range: -5.7968
Max Act: 5.1718. Min Act: -0.1700
Data Index: 7606515 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7968. Min Range: -5.7968
Max Act: 5.1718. Min Act: -0.1700
Data Index: 8573253 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7968. Min Range: -5.7968
Max Act: 5.1093. Min Act: -0.1700
Data Index: 4512529 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7968. Min Range: -5.7968
Max Act: 5.0781. Min Act: -0.1700
Data Index: 1560231 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7968. Min Range: -5.7968
Max Act: 5.0781. Min Act: -0.1700
Data Index: 7304890 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7968. Min Range: -5.7968
Max Act: 5.0468. Min Act: -0.1700
Data Index: 2981164 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7968. Min Range: -5.7968
Max Act: 5.0468. Min Act: -0.1700
Data Index: 6391510 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7968. Min Range: -5.7968
Max Act: 5.0468. Min Act: -0.1700
Data Index: 4752989 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7968. Min Range: -5.7968
Max Act: 5.0468. Min Act: -0.1700
Data Index: 2786635 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7968. Min Range: -5.7968
Max Act: 5.0156. Min Act: -0.1700
Data Index: 7574353 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7968. Min Range: -5.7968
Max Act: 5.0156. Min Act: -0.1700
Data Index: 999506 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7968. Min Range: -5.7968
Max Act: 4.9843. Min Act: -0.1700
Data Index: 1980253 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7968. Min Range: -5.7968
Max Act: 4.9843. Min Act: -0.1700
Data Index: 8647255 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19