Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3567 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.6661. Min Act: -0.1700
Data Index: 5937618 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.5723. Min Act: -0.1700
Data Index: 3206103 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.5098. Min Act: -0.1700
Data Index: 4571473 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.4786. Min Act: -0.1700
Data Index: 31096 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.4161. Min Act: -0.1700
Data Index: 4016134 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.4161. Min Act: -0.1700
Data Index: 5061177 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.4473. Min Act: -0.1700
Data Index: 1717509 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.3848. Min Act: -0.1700
Data Index: 3683979 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.4161. Min Act: -0.1700
Data Index: 3291484 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.4161. Min Act: -0.1700
Data Index: 691937 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.3848. Min Act: -0.1700
Data Index: 5715124 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.3848. Min Act: -0.1700
Data Index: 4555140 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.3848. Min Act: -0.1700
Data Index: 2254214 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.3535. Min Act: -0.1700
Data Index: 6715913 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.3848. Min Act: -0.1700
Data Index: 679255 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.3535. Min Act: -0.1700
Data Index: 2005257 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.3223. Min Act: -0.1700
Data Index: 1237257 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.3223. Min Act: -0.1700
Data Index: 4498357 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.3223. Min Act: -0.1700
Data Index: 1078522 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.3223. Min Act: -0.1700
Data Index: 1853175 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19