Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5754 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2808. Min Range: -6.2808
Max Act: 6.2808. Min Act: -0.1700
Data Index: 6571110 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.7495. Min Act: -0.1700
Data Index: 5729548 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.7183. Min Act: -0.1700
Data Index: 5392462 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.6870. Min Act: -0.1700
Data Index: 811978 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.6870. Min Act: -0.1700
Data Index: 1974212 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.6245. Min Act: -0.1700
Data Index: 5703513 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.5933. Min Act: -0.1700
Data Index: 629977 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.5308. Min Act: -0.1700
Data Index: 491353 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.5933. Min Act: -0.1700
Data Index: 7610247 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.5620. Min Act: -0.1700
Data Index: 4587760 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.5308. Min Act: -0.1700
Data Index: 2390420 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.5308. Min Act: -0.1700
Data Index: 5079154 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.5308. Min Act: -0.1700
Data Index: 2939450 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.4683. Min Act: -0.1700
Data Index: 662960 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.4683. Min Act: -0.1700
Data Index: 6838362 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.4683. Min Act: -0.1700
Data Index: 4006288 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.4370. Min Act: -0.1700
Data Index: 5560482 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.4058. Min Act: -0.1700
Data Index: 8687715 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.4370. Min Act: -0.1700
Data Index: 85488 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2808. Min Range: -6.2808
Max Act: 5.4058. Min Act: -0.1700
Data Index: 6823442 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19