Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2335 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1825. Min Range: -9.1825
Max Act: 9.1825. Min Act: -0.1700
Data Index: 740451 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1825. Min Range: -9.1825
Max Act: 8.9325. Min Act: -0.1700
Data Index: 2457558 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1825. Min Range: -9.1825
Max Act: 8.9325. Min Act: -0.1700
Data Index: 7114131 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1825. Min Range: -9.1825
Max Act: 8.7450. Min Act: -0.1700
Data Index: 5619315 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1825. Min Range: -9.1825
Max Act: 8.4950. Min Act: -0.1700
Data Index: 383113 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1825. Min Range: -9.1825
Max Act: 8.4950. Min Act: -0.1700
Data Index: 8063880 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1825. Min Range: -9.1825
Max Act: 8.3075. Min Act: -0.1700
Data Index: 1628304 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1825. Min Range: -9.1825
Max Act: 8.3075. Min Act: -0.1700
Data Index: 754402 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1825. Min Range: -9.1825
Max Act: 8.3075. Min Act: -0.1700
Data Index: 4800335 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1825. Min Range: -9.1825
Max Act: 8.2450. Min Act: -0.1700
Data Index: 38327 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1825. Min Range: -9.1825
Max Act: 8.2450. Min Act: -0.1700
Data Index: 1474672 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1825. Min Range: -9.1825
Max Act: 8.2450. Min Act: -0.1700
Data Index: 3619921 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1825. Min Range: -9.1825
Max Act: 8.1825. Min Act: -0.1700
Data Index: 3147048 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1825. Min Range: -9.1825
Max Act: 8.1825. Min Act: -0.1700
Data Index: 1369104 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1825. Min Range: -9.1825
Max Act: 8.1825. Min Act: -0.1700
Data Index: 448731 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1825. Min Range: -9.1825
Max Act: 8.2450. Min Act: -0.1700
Data Index: 1458292 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1825. Min Range: -9.1825
Max Act: 8.1825. Min Act: -0.1700
Data Index: 288080 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1825. Min Range: -9.1825
Max Act: 8.1825. Min Act: -0.1700
Data Index: 2935869 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1825. Min Range: -9.1825
Max Act: 8.1825. Min Act: -0.1700
Data Index: 3157395 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1825. Min Range: -9.1825
Max Act: 8.1200. Min Act: -0.1700
Data Index: 5212228 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19