Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2773 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3632. Min Range: -7.3632
Max Act: 7.3319. Min Act: -0.1700
Data Index: 1231095 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3632. Min Range: -7.3632
Max Act: 7.3632. Min Act: -0.1700
Data Index: 6490928 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3632. Min Range: -7.3632
Max Act: 7.3632. Min Act: -0.1700
Data Index: 3060772 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3632. Min Range: -7.3632
Max Act: 7.3319. Min Act: -0.1700
Data Index: 1643816 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3632. Min Range: -7.3632
Max Act: 7.2694. Min Act: -0.1700
Data Index: 8355894 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3632. Min Range: -7.3632
Max Act: 7.2069. Min Act: -0.1700
Data Index: 7915634 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3632. Min Range: -7.3632
Max Act: 7.1132. Min Act: -0.1700
Data Index: 8264443 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3632. Min Range: -7.3632
Max Act: 7.0819. Min Act: -0.1700
Data Index: 1488798 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3632. Min Range: -7.3632
Max Act: 7.0819. Min Act: -0.1700
Data Index: 3102177 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3632. Min Range: -7.3632
Max Act: 7.0507. Min Act: -0.1700
Data Index: 2555477 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3632. Min Range: -7.3632
Max Act: 7.0507. Min Act: -0.1700
Data Index: 2357070 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3632. Min Range: -7.3632
Max Act: 6.9882. Min Act: -0.1700
Data Index: 3003225 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3632. Min Range: -7.3632
Max Act: 6.9882. Min Act: -0.1700
Data Index: 6694332 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3632. Min Range: -7.3632
Max Act: 6.9257. Min Act: -0.1700
Data Index: 8280702 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3632. Min Range: -7.3632
Max Act: 6.9569. Min Act: -0.1700
Data Index: 3390066 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3632. Min Range: -7.3632
Max Act: 6.8944. Min Act: -0.1700
Data Index: 309928 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3632. Min Range: -7.3632
Max Act: 6.8319. Min Act: -0.1700
Data Index: 3642726 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3632. Min Range: -7.3632
Max Act: 6.8632. Min Act: -0.1700
Data Index: 1595610 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3632. Min Range: -7.3632
Max Act: 6.8007. Min Act: -0.1700
Data Index: 6252277 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3632. Min Range: -7.3632
Max Act: 6.8319. Min Act: -0.1700
Data Index: 1597033 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19