Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5984 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4650. Min Range: -6.4650
Max Act: 6.4650. Min Act: -0.1700
Data Index: 5479812 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4650. Min Range: -6.4650
Max Act: 6.2462. Min Act: -0.1700
Data Index: 1048236 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4650. Min Range: -6.4650
Max Act: 6.2150. Min Act: -0.1700
Data Index: 5945353 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4650. Min Range: -6.4650
Max Act: 6.1837. Min Act: -0.1700
Data Index: 5137348 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4650. Min Range: -6.4650
Max Act: 5.9962. Min Act: -0.1700
Data Index: 8582792 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4650. Min Range: -6.4650
Max Act: 5.9962. Min Act: -0.1700
Data Index: 8079173 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4650. Min Range: -6.4650
Max Act: 5.9962. Min Act: -0.1700
Data Index: 8617190 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4650. Min Range: -6.4650
Max Act: 5.9337. Min Act: -0.1700
Data Index: 5807955 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4650. Min Range: -6.4650
Max Act: 5.9337. Min Act: -0.1700
Data Index: 35334 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4650. Min Range: -6.4650
Max Act: 5.9337. Min Act: -0.1700
Data Index: 4079244 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4650. Min Range: -6.4650
Max Act: 5.9025. Min Act: -0.1700
Data Index: 477232 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4650. Min Range: -6.4650
Max Act: 5.9337. Min Act: -0.1700
Data Index: 467719 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4650. Min Range: -6.4650
Max Act: 5.9025. Min Act: -0.1700
Data Index: 423263 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4650. Min Range: -6.4650
Max Act: 5.9025. Min Act: -0.1700
Data Index: 7719938 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4650. Min Range: -6.4650
Max Act: 5.8712. Min Act: -0.1700
Data Index: 3763663 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4650. Min Range: -6.4650
Max Act: 5.8712. Min Act: -0.1700
Data Index: 5125414 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4650. Min Range: -6.4650
Max Act: 5.8712. Min Act: -0.1700
Data Index: 1446027 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4650. Min Range: -6.4650
Max Act: 5.8400. Min Act: -0.1700
Data Index: 7523226 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4650. Min Range: -6.4650
Max Act: 5.8400. Min Act: -0.1700
Data Index: 1620732 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4650. Min Range: -6.4650
Max Act: 5.8400. Min Act: -0.1700
Data Index: 4751917 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19