Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4291 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8197. Min Range: -6.8197
Max Act: 6.8197. Min Act: -0.1700
Data Index: 985529 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8197. Min Range: -6.8197
Max Act: 6.5072. Min Act: -0.1700
Data Index: 5462384 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8197. Min Range: -6.8197
Max Act: 6.4134. Min Act: -0.1700
Data Index: 5847358 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8197. Min Range: -6.8197
Max Act: 6.4134. Min Act: -0.1700
Data Index: 2799980 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8197. Min Range: -6.8197
Max Act: 6.4134. Min Act: -0.1700
Data Index: 5671629 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8197. Min Range: -6.8197
Max Act: 6.4134. Min Act: -0.1700
Data Index: 8258683 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8197. Min Range: -6.8197
Max Act: 6.3822. Min Act: -0.1700
Data Index: 922941 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8197. Min Range: -6.8197
Max Act: 6.2884. Min Act: -0.1700
Data Index: 8115323 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8197. Min Range: -6.8197
Max Act: 6.2884. Min Act: -0.1700
Data Index: 3429601 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8197. Min Range: -6.8197
Max Act: 6.2572. Min Act: -0.1700
Data Index: 8102785 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8197. Min Range: -6.8197
Max Act: 6.2572. Min Act: -0.1700
Data Index: 2409054 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8197. Min Range: -6.8197
Max Act: 6.2259. Min Act: -0.1700
Data Index: 6623153 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8197. Min Range: -6.8197
Max Act: 6.1947. Min Act: -0.1700
Data Index: 6100246 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8197. Min Range: -6.8197
Max Act: 6.1634. Min Act: -0.1700
Data Index: 2117119 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8197. Min Range: -6.8197
Max Act: 6.1322. Min Act: -0.1700
Data Index: 4396881 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8197. Min Range: -6.8197
Max Act: 6.1009. Min Act: -0.1700
Data Index: 930507 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8197. Min Range: -6.8197
Max Act: 6.1322. Min Act: -0.1700
Data Index: 5558297 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8197. Min Range: -6.8197
Max Act: 6.1634. Min Act: -0.1700
Data Index: 7942988 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8197. Min Range: -6.8197
Max Act: 6.1322. Min Act: -0.1700
Data Index: 7121804 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8197. Min Range: -6.8197
Max Act: 6.1322. Min Act: -0.1700
Data Index: 1751914 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19