Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6033 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5918. Min Range: -4.5918
Max Act: 4.5918. Min Act: -0.1700
Data Index: 6290247 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5918. Min Range: -4.5918
Max Act: 4.5918. Min Act: -0.1700
Data Index: 3268362 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5918. Min Range: -4.5918
Max Act: 4.5293. Min Act: -0.1700
Data Index: 1239887 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5918. Min Range: -4.5918
Max Act: 4.4981. Min Act: -0.1700
Data Index: 5556660 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5918. Min Range: -4.5918
Max Act: 4.5293. Min Act: -0.1700
Data Index: 3210958 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5918. Min Range: -4.5918
Max Act: 4.4981. Min Act: -0.1700
Data Index: 2689930 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5918. Min Range: -4.5918
Max Act: 4.4981. Min Act: -0.1700
Data Index: 8235420 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5918. Min Range: -4.5918
Max Act: 4.4668. Min Act: -0.1700
Data Index: 3383005 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5918. Min Range: -4.5918
Max Act: 4.4981. Min Act: -0.1700
Data Index: 8647057 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5918. Min Range: -4.5918
Max Act: 4.4356. Min Act: -0.1700
Data Index: 7421423 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5918. Min Range: -4.5918
Max Act: 4.4356. Min Act: -0.1700
Data Index: 408459 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5918. Min Range: -4.5918
Max Act: 4.4356. Min Act: -0.1700
Data Index: 5157505 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5918. Min Range: -4.5918
Max Act: 4.4043. Min Act: -0.1700
Data Index: 3867995 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5918. Min Range: -4.5918
Max Act: 4.4043. Min Act: -0.1700
Data Index: 6301014 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5918. Min Range: -4.5918
Max Act: 4.4043. Min Act: -0.1700
Data Index: 4713493 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5918. Min Range: -4.5918
Max Act: 4.4043. Min Act: -0.1700
Data Index: 2210139 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5918. Min Range: -4.5918
Max Act: 4.4043. Min Act: -0.1700
Data Index: 3319307 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5918. Min Range: -4.5918
Max Act: 4.3731. Min Act: -0.1700
Data Index: 7005715 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5918. Min Range: -4.5918
Max Act: 4.3731. Min Act: -0.1700
Data Index: 8120526 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5918. Min Range: -4.5918
Max Act: 4.3731. Min Act: -0.1700
Data Index: 8819358 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19