Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4359 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8211. Min Range: -9.8211
Max Act: 9.8211. Min Act: -0.1700
Data Index: 8799169 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8211. Min Range: -9.8211
Max Act: 9.5711. Min Act: -0.1700
Data Index: 8216128 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8211. Min Range: -9.8211
Max Act: 9.5711. Min Act: -0.1700
Data Index: 852837 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8211. Min Range: -9.8211
Max Act: 9.3836. Min Act: -0.1700
Data Index: 5268535 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8211. Min Range: -9.8211
Max Act: 9.3211. Min Act: -0.1700
Data Index: 7739092 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8211. Min Range: -9.8211
Max Act: 9.3211. Min Act: -0.1700
Data Index: 8199477 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8211. Min Range: -9.8211
Max Act: 9.2586. Min Act: -0.1700
Data Index: 3258344 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8211. Min Range: -9.8211
Max Act: 9.2586. Min Act: -0.1700
Data Index: 6549259 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8211. Min Range: -9.8211
Max Act: 9.2586. Min Act: -0.1700
Data Index: 1221068 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8211. Min Range: -9.8211
Max Act: 9.2586. Min Act: -0.1700
Data Index: 7134510 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8211. Min Range: -9.8211
Max Act: 9.1961. Min Act: -0.1700
Data Index: 4315168 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8211. Min Range: -9.8211
Max Act: 9.1961. Min Act: -0.1700
Data Index: 2112973 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8211. Min Range: -9.8211
Max Act: 9.1961. Min Act: -0.1700
Data Index: 7058630 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8211. Min Range: -9.8211
Max Act: 9.0711. Min Act: -0.1700
Data Index: 1041327 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8211. Min Range: -9.8211
Max Act: 9.0711. Min Act: -0.1700
Data Index: 7009618 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8211. Min Range: -9.8211
Max Act: 9.1336. Min Act: -0.1700
Data Index: 4572455 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8211. Min Range: -9.8211
Max Act: 8.9461. Min Act: -0.1700
Data Index: 2399627 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8211. Min Range: -9.8211
Max Act: 8.8836. Min Act: -0.1700
Data Index: 1465524 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8211. Min Range: -9.8211
Max Act: 8.8836. Min Act: -0.1700
Data Index: 8262148 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8211. Min Range: -9.8211
Max Act: 8.8836. Min Act: -0.1700
Data Index: 1253173 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19