Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5633 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.7677. Min Act: -0.1700
Data Index: 1343590 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.7677. Min Act: -0.1700
Data Index: 4808026 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.2990. Min Act: -0.1700
Data Index: 1683740 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.2365. Min Act: -0.1700
Data Index: 4242251 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.0802. Min Act: -0.1700
Data Index: 1268232 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7677. Min Range: -7.7677
Max Act: 6.9240. Min Act: -0.1700
Data Index: 288209 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7677. Min Range: -7.7677
Max Act: 6.8927. Min Act: -0.1700
Data Index: 2992293 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7677. Min Range: -7.7677
Max Act: 6.8615. Min Act: -0.1700
Data Index: 636639 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7677. Min Range: -7.7677
Max Act: 6.8615. Min Act: -0.1700
Data Index: 362819 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7677. Min Range: -7.7677
Max Act: 6.8615. Min Act: -0.1700
Data Index: 5048634 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7677. Min Range: -7.7677
Max Act: 6.7990. Min Act: -0.1700
Data Index: 7081673 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7677. Min Range: -7.7677
Max Act: 6.8302. Min Act: -0.1700
Data Index: 3404774 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7677. Min Range: -7.7677
Max Act: 6.7990. Min Act: -0.1700
Data Index: 575849 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7677. Min Range: -7.7677
Max Act: 6.7677. Min Act: -0.1700
Data Index: 688618 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7677. Min Range: -7.7677
Max Act: 6.7677. Min Act: -0.1700
Data Index: 370820 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7677. Min Range: -7.7677
Max Act: 6.7677. Min Act: -0.1700
Data Index: 4298179 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7677. Min Range: -7.7677
Max Act: 6.7677. Min Act: -0.1700
Data Index: 7879878 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7677. Min Range: -7.7677
Max Act: 6.7365. Min Act: -0.1700
Data Index: 29568 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7677. Min Range: -7.7677
Max Act: 6.7052. Min Act: -0.1700
Data Index: 4195011 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7677. Min Range: -7.7677
Max Act: 6.7677. Min Act: -0.1700
Data Index: 998753 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19