Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2975 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5497. Min Range: -7.5497
Max Act: 7.5497. Min Act: -0.1700
Data Index: 6760005 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5497. Min Range: -7.5497
Max Act: 7.3934. Min Act: -0.1700
Data Index: 8146104 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5497. Min Range: -7.5497
Max Act: 7.2997. Min Act: -0.1700
Data Index: 6585130 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5497. Min Range: -7.5497
Max Act: 7.2372. Min Act: -0.1700
Data Index: 5950452 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5497. Min Range: -7.5497
Max Act: 7.2372. Min Act: -0.1700
Data Index: 5431015 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5497. Min Range: -7.5497
Max Act: 7.2059. Min Act: -0.1700
Data Index: 2696239 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5497. Min Range: -7.5497
Max Act: 7.0497. Min Act: -0.1700
Data Index: 973098 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5497. Min Range: -7.5497
Max Act: 7.0497. Min Act: -0.1700
Data Index: 1731316 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5497. Min Range: -7.5497
Max Act: 7.0184. Min Act: -0.1700
Data Index: 6587633 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5497. Min Range: -7.5497
Max Act: 6.9872. Min Act: -0.1700
Data Index: 4417004 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5497. Min Range: -7.5497
Max Act: 6.9872. Min Act: -0.1700
Data Index: 3643782 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5497. Min Range: -7.5497
Max Act: 6.9872. Min Act: -0.1700
Data Index: 2314413 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5497. Min Range: -7.5497
Max Act: 6.9559. Min Act: -0.1700
Data Index: 959707 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5497. Min Range: -7.5497
Max Act: 6.9559. Min Act: -0.1700
Data Index: 1016241 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5497. Min Range: -7.5497
Max Act: 6.9559. Min Act: -0.1700
Data Index: 6463111 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5497. Min Range: -7.5497
Max Act: 6.9247. Min Act: -0.1700
Data Index: 2219146 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5497. Min Range: -7.5497
Max Act: 6.9247. Min Act: -0.1700
Data Index: 614056 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5497. Min Range: -7.5497
Max Act: 6.9247. Min Act: -0.1700
Data Index: 2621356 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5497. Min Range: -7.5497
Max Act: 6.8934. Min Act: -0.1700
Data Index: 2174414 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5497. Min Range: -7.5497
Max Act: 6.9247. Min Act: -0.1700
Data Index: 5264166 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19