Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4311 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2338. Min Range: -4.2338
Max Act: 4.2338. Min Act: -0.1700
Data Index: 5176123 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2338. Min Range: -4.2338
Max Act: 4.1400. Min Act: -0.1700
Data Index: 2036581 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2338. Min Range: -4.2338
Max Act: 4.1400. Min Act: -0.1700
Data Index: 2380666 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2338. Min Range: -4.2338
Max Act: 3.9525. Min Act: -0.1700
Data Index: 3082539 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2338. Min Range: -4.2338
Max Act: 3.9525. Min Act: -0.1700
Data Index: 2296248 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2338. Min Range: -4.2338
Max Act: 3.9525. Min Act: -0.1700
Data Index: 6427373 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2338. Min Range: -4.2338
Max Act: 3.9525. Min Act: -0.1700
Data Index: 3764836 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2338. Min Range: -4.2338
Max Act: 3.8900. Min Act: -0.1700
Data Index: 7305831 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2338. Min Range: -4.2338
Max Act: 3.8900. Min Act: -0.1700
Data Index: 6822692 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2338. Min Range: -4.2338
Max Act: 3.9212. Min Act: -0.1700
Data Index: 201410 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2338. Min Range: -4.2338
Max Act: 3.8900. Min Act: -0.1700
Data Index: 2147605 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2338. Min Range: -4.2338
Max Act: 3.8587. Min Act: -0.1700
Data Index: 7466688 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2338. Min Range: -4.2338
Max Act: 3.8900. Min Act: -0.1700
Data Index: 7365949 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2338. Min Range: -4.2338
Max Act: 3.8587. Min Act: -0.1700
Data Index: 790704 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2338. Min Range: -4.2338
Max Act: 3.7961. Min Act: -0.1700
Data Index: 3945749 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2338. Min Range: -4.2338
Max Act: 3.8274. Min Act: -0.1700
Data Index: 768560 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2338. Min Range: -4.2338
Max Act: 3.7649. Min Act: -0.1700
Data Index: 8421739 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2338. Min Range: -4.2338
Max Act: 3.7023. Min Act: -0.1700
Data Index: 2490182 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2338. Min Range: -4.2338
Max Act: 3.7023. Min Act: -0.1700
Data Index: 5404282 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2338. Min Range: -4.2338
Max Act: 3.7023. Min Act: -0.1700
Data Index: 3190871 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19