Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3378 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4069. Min Range: -7.4069
Max Act: 7.4069. Min Act: -0.1700
Data Index: 4041413 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4069. Min Range: -7.4069
Max Act: 7.2194. Min Act: -0.1700
Data Index: 6124794 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4069. Min Range: -7.4069
Max Act: 7.2194. Min Act: -0.1700
Data Index: 6997803 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4069. Min Range: -7.4069
Max Act: 7.1257. Min Act: -0.1700
Data Index: 6147412 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4069. Min Range: -7.4069
Max Act: 7.0944. Min Act: -0.1700
Data Index: 7429315 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4069. Min Range: -7.4069
Max Act: 6.7819. Min Act: -0.1700
Data Index: 3687649 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4069. Min Range: -7.4069
Max Act: 6.7507. Min Act: -0.1700
Data Index: 4855561 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4069. Min Range: -7.4069
Max Act: 6.7507. Min Act: -0.1700
Data Index: 7730258 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4069. Min Range: -7.4069
Max Act: 6.7194. Min Act: -0.1700
Data Index: 1950578 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4069. Min Range: -7.4069
Max Act: 6.6882. Min Act: -0.1700
Data Index: 2123932 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4069. Min Range: -7.4069
Max Act: 6.6882. Min Act: -0.1700
Data Index: 7812170 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4069. Min Range: -7.4069
Max Act: 6.6569. Min Act: -0.1700
Data Index: 6632872 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4069. Min Range: -7.4069
Max Act: 6.6882. Min Act: -0.1700
Data Index: 208445 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4069. Min Range: -7.4069
Max Act: 6.6569. Min Act: -0.1700
Data Index: 1245152 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4069. Min Range: -7.4069
Max Act: 6.6569. Min Act: -0.1700
Data Index: 3366917 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4069. Min Range: -7.4069
Max Act: 6.6257. Min Act: -0.1700
Data Index: 7889339 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4069. Min Range: -7.4069
Max Act: 6.6257. Min Act: -0.1700
Data Index: 6754043 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4069. Min Range: -7.4069
Max Act: 6.5944. Min Act: -0.1700
Data Index: 5130628 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4069. Min Range: -7.4069
Max Act: 6.6257. Min Act: -0.1700
Data Index: 2938867 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4069. Min Range: -7.4069
Max Act: 6.6257. Min Act: -0.1700
Data Index: 2598493 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19