Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4820 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6266. Min Range: -5.6266
Max Act: 5.6266. Min Act: -0.1700
Data Index: 5528997 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6266. Min Range: -5.6266
Max Act: 5.5016. Min Act: -0.1700
Data Index: 325697 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6266. Min Range: -5.6266
Max Act: 5.4391. Min Act: -0.1700
Data Index: 4692413 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6266. Min Range: -5.6266
Max Act: 5.4391. Min Act: -0.1700
Data Index: 1713997 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6266. Min Range: -5.6266
Max Act: 5.4078. Min Act: -0.1700
Data Index: 7381964 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6266. Min Range: -5.6266
Max Act: 5.3766. Min Act: -0.1700
Data Index: 3240162 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6266. Min Range: -5.6266
Max Act: 5.3766. Min Act: -0.1700
Data Index: 8429350 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6266. Min Range: -5.6266
Max Act: 5.3453. Min Act: -0.1700
Data Index: 58653 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6266. Min Range: -5.6266
Max Act: 5.3453. Min Act: -0.1700
Data Index: 1947961 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6266. Min Range: -5.6266
Max Act: 5.3141. Min Act: -0.1700
Data Index: 6146057 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6266. Min Range: -5.6266
Max Act: 5.2516. Min Act: -0.1700
Data Index: 2110144 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6266. Min Range: -5.6266
Max Act: 5.2203. Min Act: -0.1700
Data Index: 1958079 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6266. Min Range: -5.6266
Max Act: 5.2516. Min Act: -0.1700
Data Index: 594111 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6266. Min Range: -5.6266
Max Act: 5.1891. Min Act: -0.1700
Data Index: 5602089 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6266. Min Range: -5.6266
Max Act: 5.1891. Min Act: -0.1700
Data Index: 1946445 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6266. Min Range: -5.6266
Max Act: 5.1891. Min Act: -0.1700
Data Index: 4346264 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6266. Min Range: -5.6266
Max Act: 5.1578. Min Act: -0.1700
Data Index: 797374 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6266. Min Range: -5.6266
Max Act: 5.1266. Min Act: -0.1700
Data Index: 7566634 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6266. Min Range: -5.6266
Max Act: 5.1266. Min Act: -0.1700
Data Index: 4935834 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6266. Min Range: -5.6266
Max Act: 5.0953. Min Act: -0.1700
Data Index: 3561043 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19