Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4827 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6838. Min Range: -4.6838
Max Act: 4.6838. Min Act: -0.1700
Data Index: 2545892 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6838. Min Range: -4.6838
Max Act: 4.4651. Min Act: -0.1700
Data Index: 3109257 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6838. Min Range: -4.6838
Max Act: 4.4338. Min Act: -0.1700
Data Index: 1285236 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6838. Min Range: -4.6838
Max Act: 4.4026. Min Act: -0.1700
Data Index: 1228043 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6838. Min Range: -4.6838
Max Act: 4.4026. Min Act: -0.1700
Data Index: 4511424 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6838. Min Range: -4.6838
Max Act: 4.4338. Min Act: -0.1700
Data Index: 5758032 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6838. Min Range: -4.6838
Max Act: 4.3401. Min Act: -0.1700
Data Index: 5328871 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6838. Min Range: -4.6838
Max Act: 4.3088. Min Act: -0.1700
Data Index: 3386906 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6838. Min Range: -4.6838
Max Act: 4.2776. Min Act: -0.1700
Data Index: 2382250 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6838. Min Range: -4.6838
Max Act: 4.2463. Min Act: -0.1700
Data Index: 3247274 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6838. Min Range: -4.6838
Max Act: 4.2151. Min Act: -0.1700
Data Index: 8609094 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6838. Min Range: -4.6838
Max Act: 4.2776. Min Act: -0.1700
Data Index: 8311724 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6838. Min Range: -4.6838
Max Act: 4.2151. Min Act: -0.1700
Data Index: 3480815 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6838. Min Range: -4.6838
Max Act: 4.1838. Min Act: -0.1700
Data Index: 1262617 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6838. Min Range: -4.6838
Max Act: 4.2151. Min Act: -0.1700
Data Index: 1404430 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6838. Min Range: -4.6838
Max Act: 4.1838. Min Act: -0.1700
Data Index: 5944533 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6838. Min Range: -4.6838
Max Act: 4.1838. Min Act: -0.1700
Data Index: 2615394 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6838. Min Range: -4.6838
Max Act: 4.1838. Min Act: -0.1700
Data Index: 2209494 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6838. Min Range: -4.6838
Max Act: 4.1526. Min Act: -0.1700
Data Index: 2082527 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6838. Min Range: -4.6838
Max Act: 4.1526. Min Act: -0.1700
Data Index: 7326913 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19