Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4723 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7856. Min Range: -6.7856
Max Act: 6.7856. Min Act: -0.1700
Data Index: 6838428 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7856. Min Range: -6.7856
Max Act: 6.6294. Min Act: -0.1700
Data Index: 1098090 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7856. Min Range: -6.7856
Max Act: 6.5356. Min Act: -0.1700
Data Index: 61517 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7856. Min Range: -6.7856
Max Act: 6.5044. Min Act: -0.1700
Data Index: 3965097 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7856. Min Range: -6.7856
Max Act: 6.5044. Min Act: -0.1700
Data Index: 7168758 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7856. Min Range: -6.7856
Max Act: 6.4731. Min Act: -0.1700
Data Index: 7619208 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7856. Min Range: -6.7856
Max Act: 6.4731. Min Act: -0.1700
Data Index: 2348453 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7856. Min Range: -6.7856
Max Act: 6.4106. Min Act: -0.1700
Data Index: 7320440 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7856. Min Range: -6.7856
Max Act: 6.3481. Min Act: -0.1700
Data Index: 2846274 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7856. Min Range: -6.7856
Max Act: 6.3169. Min Act: -0.1700
Data Index: 3724743 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7856. Min Range: -6.7856
Max Act: 6.2856. Min Act: -0.1700
Data Index: 1928115 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7856. Min Range: -6.7856
Max Act: 6.2544. Min Act: -0.1700
Data Index: 1848368 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7856. Min Range: -6.7856
Max Act: 6.2544. Min Act: -0.1700
Data Index: 7705549 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7856. Min Range: -6.7856
Max Act: 6.2231. Min Act: -0.1700
Data Index: 4440683 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7856. Min Range: -6.7856
Max Act: 6.2544. Min Act: -0.1700
Data Index: 6714299 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7856. Min Range: -6.7856
Max Act: 6.1606. Min Act: -0.1700
Data Index: 1714063 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7856. Min Range: -6.7856
Max Act: 6.1606. Min Act: -0.1700
Data Index: 5909673 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7856. Min Range: -6.7856
Max Act: 6.1606. Min Act: -0.1700
Data Index: 6447247 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7856. Min Range: -6.7856
Max Act: 6.1606. Min Act: -0.1700
Data Index: 4247476 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7856. Min Range: -6.7856
Max Act: 6.1919. Min Act: -0.1700
Data Index: 1696230 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19