Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 511 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2036. Min Range: -2.2036
Max Act: 2.2036. Min Act: -0.1700
Data Index: 4541044 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2036. Min Range: -2.2036
Max Act: 2.1870. Min Act: -0.1700
Data Index: 5394669 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2036. Min Range: -2.2036
Max Act: 2.1870. Min Act: -0.1700
Data Index: 7756315 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2036. Min Range: -2.2036
Max Act: 2.1870. Min Act: -0.1700
Data Index: 4376241 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2036. Min Range: -2.2036
Max Act: 2.1537. Min Act: -0.1700
Data Index: 8420036 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2036. Min Range: -2.2036
Max Act: 2.1537. Min Act: -0.1700
Data Index: 8591771 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2036. Min Range: -2.2036
Max Act: 2.1537. Min Act: -0.1700
Data Index: 1696823 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2036. Min Range: -2.2036
Max Act: 2.1537. Min Act: -0.1700
Data Index: 6716936 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2036. Min Range: -2.2036
Max Act: 2.1371. Min Act: -0.1700
Data Index: 1243680 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2036. Min Range: -2.2036
Max Act: 2.1537. Min Act: -0.1700
Data Index: 5954363 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2036. Min Range: -2.2036
Max Act: 2.1371. Min Act: -0.1700
Data Index: 1083674 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2036. Min Range: -2.2036
Max Act: 2.1371. Min Act: -0.1700
Data Index: 285914 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2036. Min Range: -2.2036
Max Act: 2.1371. Min Act: -0.1700
Data Index: 6008983 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2036. Min Range: -2.2036
Max Act: 2.1371. Min Act: -0.1700
Data Index: 5966659 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2036. Min Range: -2.2036
Max Act: 2.1371. Min Act: -0.1700
Data Index: 8397445 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2036. Min Range: -2.2036
Max Act: 2.1371. Min Act: -0.1700
Data Index: 5365483 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2036. Min Range: -2.2036
Max Act: 2.1371. Min Act: -0.1700
Data Index: 5145272 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2036. Min Range: -2.2036
Max Act: 2.1204. Min Act: -0.1700
Data Index: 5668411 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2036. Min Range: -2.2036
Max Act: 2.1204. Min Act: -0.1700
Data Index: 5879637 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2036. Min Range: -2.2036
Max Act: 2.1204. Min Act: -0.1700
Data Index: 4193902 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19