Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3103 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8883. Min Range: -6.8883
Max Act: 6.8883. Min Act: -0.1700
Data Index: 8293784 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8883. Min Range: -6.8883
Max Act: 6.7633. Min Act: -0.1700
Data Index: 5848449 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8883. Min Range: -6.8883
Max Act: 6.7321. Min Act: -0.1700
Data Index: 7867671 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8883. Min Range: -6.8883
Max Act: 6.7008. Min Act: -0.1700
Data Index: 1018732 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8883. Min Range: -6.8883
Max Act: 6.7008. Min Act: -0.1700
Data Index: 3809280 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8883. Min Range: -6.8883
Max Act: 6.6383. Min Act: -0.1700
Data Index: 1864934 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8883. Min Range: -6.8883
Max Act: 6.6383. Min Act: -0.1700
Data Index: 3811395 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8883. Min Range: -6.8883
Max Act: 6.6383. Min Act: -0.1700
Data Index: 1975129 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8883. Min Range: -6.8883
Max Act: 6.6383. Min Act: -0.1700
Data Index: 4810929 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8883. Min Range: -6.8883
Max Act: 6.6383. Min Act: -0.1700
Data Index: 5280672 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8883. Min Range: -6.8883
Max Act: 6.6383. Min Act: -0.1700
Data Index: 2111661 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8883. Min Range: -6.8883
Max Act: 6.6071. Min Act: -0.1700
Data Index: 8068634 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8883. Min Range: -6.8883
Max Act: 6.6383. Min Act: -0.1700
Data Index: 4853334 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8883. Min Range: -6.8883
Max Act: 6.6071. Min Act: -0.1700
Data Index: 4762353 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8883. Min Range: -6.8883
Max Act: 6.6071. Min Act: -0.1700
Data Index: 7518195 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8883. Min Range: -6.8883
Max Act: 6.6071. Min Act: -0.1700
Data Index: 7923342 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8883. Min Range: -6.8883
Max Act: 6.5758. Min Act: -0.1700
Data Index: 4246470 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8883. Min Range: -6.8883
Max Act: 6.5446. Min Act: -0.1700
Data Index: 3929242 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8883. Min Range: -6.8883
Max Act: 6.5133. Min Act: -0.1700
Data Index: 238287 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8883. Min Range: -6.8883
Max Act: 6.5133. Min Act: -0.1700
Data Index: 2235398 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19