Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2777 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6874. Min Range: -5.6874
Max Act: 5.6874. Min Act: -0.1700
Data Index: 2398783 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6874. Min Range: -5.6874
Max Act: 5.5937. Min Act: -0.1700
Data Index: 6261931 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6874. Min Range: -5.6874
Max Act: 5.4374. Min Act: -0.1700
Data Index: 4353091 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6874. Min Range: -5.6874
Max Act: 5.4374. Min Act: -0.1700
Data Index: 5909778 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6874. Min Range: -5.6874
Max Act: 5.4062. Min Act: -0.1700
Data Index: 8286483 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6874. Min Range: -5.6874
Max Act: 5.4062. Min Act: -0.1700
Data Index: 541282 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6874. Min Range: -5.6874
Max Act: 5.3749. Min Act: -0.1700
Data Index: 1931318 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6874. Min Range: -5.6874
Max Act: 5.3749. Min Act: -0.1700
Data Index: 7041393 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6874. Min Range: -5.6874
Max Act: 5.3749. Min Act: -0.1700
Data Index: 25722 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6874. Min Range: -5.6874
Max Act: 5.3749. Min Act: -0.1700
Data Index: 4861689 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6874. Min Range: -5.6874
Max Act: 5.3124. Min Act: -0.1700
Data Index: 8178325 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6874. Min Range: -5.6874
Max Act: 5.3437. Min Act: -0.1700
Data Index: 3649255 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6874. Min Range: -5.6874
Max Act: 5.3124. Min Act: -0.1700
Data Index: 3198072 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6874. Min Range: -5.6874
Max Act: 5.3124. Min Act: -0.1700
Data Index: 2954819 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6874. Min Range: -5.6874
Max Act: 5.3124. Min Act: -0.1700
Data Index: 3010575 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6874. Min Range: -5.6874
Max Act: 5.3124. Min Act: -0.1700
Data Index: 6819164 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6874. Min Range: -5.6874
Max Act: 5.2812. Min Act: -0.1700
Data Index: 6046197 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6874. Min Range: -5.6874
Max Act: 5.2812. Min Act: -0.1700
Data Index: 6951530 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6874. Min Range: -5.6874
Max Act: 5.2812. Min Act: -0.1700
Data Index: 3208638 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6874. Min Range: -5.6874
Max Act: 5.2812. Min Act: -0.1700
Data Index: 3926308 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19