Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2986 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2324. Min Range: -7.2324
Max Act: 7.2324. Min Act: -0.1700
Data Index: 1900646 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2324. Min Range: -7.2324
Max Act: 7.0449. Min Act: -0.1700
Data Index: 5254643 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2324. Min Range: -7.2324
Max Act: 7.0136. Min Act: -0.1700
Data Index: 1215527 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2324. Min Range: -7.2324
Max Act: 6.9824. Min Act: -0.1700
Data Index: 3715366 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2324. Min Range: -7.2324
Max Act: 6.8886. Min Act: -0.1700
Data Index: 3073191 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2324. Min Range: -7.2324
Max Act: 6.8886. Min Act: -0.1700
Data Index: 4390403 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2324. Min Range: -7.2324
Max Act: 6.8886. Min Act: -0.1700
Data Index: 2608670 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2324. Min Range: -7.2324
Max Act: 6.8261. Min Act: -0.1700
Data Index: 921913 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2324. Min Range: -7.2324
Max Act: 6.7636. Min Act: -0.1700
Data Index: 1123527 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2324. Min Range: -7.2324
Max Act: 6.7324. Min Act: -0.1700
Data Index: 826256 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2324. Min Range: -7.2324
Max Act: 6.7324. Min Act: -0.1700
Data Index: 8144626 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2324. Min Range: -7.2324
Max Act: 6.7011. Min Act: -0.1700
Data Index: 6225959 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2324. Min Range: -7.2324
Max Act: 6.6699. Min Act: -0.1700
Data Index: 4181385 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2324. Min Range: -7.2324
Max Act: 6.6699. Min Act: -0.1700
Data Index: 6927959 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2324. Min Range: -7.2324
Max Act: 6.6386. Min Act: -0.1700
Data Index: 2530884 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2324. Min Range: -7.2324
Max Act: 6.6074. Min Act: -0.1700
Data Index: 1124641 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2324. Min Range: -7.2324
Max Act: 6.6074. Min Act: -0.1700
Data Index: 548330 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2324. Min Range: -7.2324
Max Act: 6.6074. Min Act: -0.1700
Data Index: 8343730 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2324. Min Range: -7.2324
Max Act: 6.5761. Min Act: -0.1700
Data Index: 5187946 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2324. Min Range: -7.2324
Max Act: 6.5449. Min Act: -0.1700
Data Index: 7998759 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19