Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3019 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8289. Min Range: -8.8289
Max Act: 8.8289. Min Act: -0.1700
Data Index: 6813733 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8289. Min Range: -8.8289
Max Act: 8.7039. Min Act: -0.1700
Data Index: 6077428 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8289. Min Range: -8.8289
Max Act: 8.5789. Min Act: -0.1700
Data Index: 3779072 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8289. Min Range: -8.8289
Max Act: 8.4539. Min Act: -0.1700
Data Index: 2082754 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8289. Min Range: -8.8289
Max Act: 8.2664. Min Act: -0.1700
Data Index: 2687422 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8289. Min Range: -8.8289
Max Act: 8.2039. Min Act: -0.1700
Data Index: 897605 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8289. Min Range: -8.8289
Max Act: 7.9227. Min Act: -0.1700
Data Index: 1403849 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8289. Min Range: -8.8289
Max Act: 7.9227. Min Act: -0.1700
Data Index: 932481 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8289. Min Range: -8.8289
Max Act: 7.8289. Min Act: -0.1700
Data Index: 2882046 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8289. Min Range: -8.8289
Max Act: 7.8289. Min Act: -0.1700
Data Index: 4992304 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8289. Min Range: -8.8289
Max Act: 7.7664. Min Act: -0.1700
Data Index: 3780416 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8289. Min Range: -8.8289
Max Act: 7.7352. Min Act: -0.1700
Data Index: 8564461 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8289. Min Range: -8.8289
Max Act: 7.7039. Min Act: -0.1700
Data Index: 2843328 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8289. Min Range: -8.8289
Max Act: 7.7039. Min Act: -0.1700
Data Index: 2669187 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8289. Min Range: -8.8289
Max Act: 7.6414. Min Act: -0.1700
Data Index: 4689584 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8289. Min Range: -8.8289
Max Act: 7.6102. Min Act: -0.1700
Data Index: 3272140 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8289. Min Range: -8.8289
Max Act: 7.6102. Min Act: -0.1700
Data Index: 1250204 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8289. Min Range: -8.8289
Max Act: 7.5789. Min Act: -0.1700
Data Index: 7769107 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8289. Min Range: -8.8289
Max Act: 7.5164. Min Act: -0.1700
Data Index: 5070565 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8289. Min Range: -8.8289
Max Act: 7.4227. Min Act: -0.1700
Data Index: 5143139 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19