Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 853 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3071. Min Range: -7.3071
Max Act: 7.3071. Min Act: -0.1700
Data Index: 3572354 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3071. Min Range: -7.3071
Max Act: 6.8071. Min Act: -0.1700
Data Index: 6189214 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3071. Min Range: -7.3071
Max Act: 6.8071. Min Act: -0.1700
Data Index: 2984543 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3071. Min Range: -7.3071
Max Act: 6.7758. Min Act: -0.1700
Data Index: 1864590 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3071. Min Range: -7.3071
Max Act: 6.7446. Min Act: -0.1700
Data Index: 2503541 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3071. Min Range: -7.3071
Max Act: 6.7446. Min Act: -0.1700
Data Index: 4484232 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3071. Min Range: -7.3071
Max Act: 6.6508. Min Act: -0.1700
Data Index: 541439 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3071. Min Range: -7.3071
Max Act: 6.6196. Min Act: -0.1700
Data Index: 7810364 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3071. Min Range: -7.3071
Max Act: 6.5883. Min Act: -0.1700
Data Index: 5877466 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3071. Min Range: -7.3071
Max Act: 6.5883. Min Act: -0.1700
Data Index: 3571531 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3071. Min Range: -7.3071
Max Act: 6.5883. Min Act: -0.1700
Data Index: 2209884 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3071. Min Range: -7.3071
Max Act: 6.5883. Min Act: -0.1700
Data Index: 3654964 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3071. Min Range: -7.3071
Max Act: 6.5571. Min Act: -0.1700
Data Index: 3757926 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3071. Min Range: -7.3071
Max Act: 6.5258. Min Act: -0.1700
Data Index: 5934885 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3071. Min Range: -7.3071
Max Act: 6.5883. Min Act: -0.1700
Data Index: 1587510 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3071. Min Range: -7.3071
Max Act: 6.5258. Min Act: -0.1700
Data Index: 8822128 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3071. Min Range: -7.3071
Max Act: 6.4946. Min Act: -0.1700
Data Index: 6801421 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3071. Min Range: -7.3071
Max Act: 6.5258. Min Act: -0.1700
Data Index: 4775553 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3071. Min Range: -7.3071
Max Act: 6.4946. Min Act: -0.1700
Data Index: 8173758 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3071. Min Range: -7.3071
Max Act: 6.4946. Min Act: -0.1700
Data Index: 838954 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19