Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3030 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5414. Min Range: -4.5414
Max Act: 4.5414. Min Act: -0.1700
Data Index: 8226543 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5414. Min Range: -4.5414
Max Act: 4.4476. Min Act: -0.1700
Data Index: 4245621 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5414. Min Range: -4.5414
Max Act: 4.3539. Min Act: -0.1700
Data Index: 3490199 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5414. Min Range: -4.5414
Max Act: 4.3226. Min Act: -0.1700
Data Index: 7654379 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5414. Min Range: -4.5414
Max Act: 4.3226. Min Act: -0.1700
Data Index: 8304705 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5414. Min Range: -4.5414
Max Act: 4.3539. Min Act: -0.1700
Data Index: 406285 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5414. Min Range: -4.5414
Max Act: 4.1976. Min Act: -0.1700
Data Index: 7654385 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5414. Min Range: -4.5414
Max Act: 4.2289. Min Act: -0.1700
Data Index: 5171451 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5414. Min Range: -4.5414
Max Act: 4.2289. Min Act: -0.1700
Data Index: 206797 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5414. Min Range: -4.5414
Max Act: 4.2289. Min Act: -0.1700
Data Index: 4092257 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5414. Min Range: -4.5414
Max Act: 4.1976. Min Act: -0.1700
Data Index: 1150652 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5414. Min Range: -4.5414
Max Act: 4.1976. Min Act: -0.1700
Data Index: 7727268 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5414. Min Range: -4.5414
Max Act: 4.1664. Min Act: -0.1700
Data Index: 8728217 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5414. Min Range: -4.5414
Max Act: 4.1664. Min Act: -0.1700
Data Index: 812499 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5414. Min Range: -4.5414
Max Act: 4.1351. Min Act: -0.1700
Data Index: 1591421 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5414. Min Range: -4.5414
Max Act: 4.1351. Min Act: -0.1700
Data Index: 273460 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5414. Min Range: -4.5414
Max Act: 4.1351. Min Act: -0.1700
Data Index: 4753453 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5414. Min Range: -4.5414
Max Act: 4.1351. Min Act: -0.1700
Data Index: 5053257 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5414. Min Range: -4.5414
Max Act: 4.1039. Min Act: -0.1700
Data Index: 4099835 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5414. Min Range: -4.5414
Max Act: 4.1039. Min Act: -0.1700
Data Index: 5489809 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19