Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5633 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.4432. Min Act: -0.1700
Data Index: 6829847 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.3807. Min Act: -0.1700
Data Index: 5258925 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.3494. Min Act: -0.1700
Data Index: 3385082 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.3182. Min Act: -0.1700
Data Index: 6637554 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.3182. Min Act: -0.1700
Data Index: 4502588 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.2869. Min Act: -0.1700
Data Index: 6399196 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.2869. Min Act: -0.1700
Data Index: 465090 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.2869. Min Act: -0.1700
Data Index: 4239623 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.2244. Min Act: -0.1700
Data Index: 2947253 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.1619. Min Act: -0.1700
Data Index: 8113694 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.1619. Min Act: -0.1700
Data Index: 3313405 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.1307. Min Act: -0.1700
Data Index: 5739826 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.1619. Min Act: -0.1700
Data Index: 7744556 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.1307. Min Act: -0.1700
Data Index: 305266 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.1307. Min Act: -0.1700
Data Index: 3852222 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.0994. Min Act: -0.1700
Data Index: 8398152 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.0994. Min Act: -0.1700
Data Index: 305265 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.0682. Min Act: -0.1700
Data Index: 7237882 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.0682. Min Act: -0.1700
Data Index: 840780 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.0682. Min Act: -0.1700
Data Index: 5446753 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19