Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2303 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0561. Min Range: -9.0561
Max Act: 9.0561. Min Act: -0.1700
Data Index: 7718431 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0561. Min Range: -9.0561
Max Act: 9.0561. Min Act: -0.1700
Data Index: 6705699 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0561. Min Range: -9.0561
Max Act: 8.9936. Min Act: -0.1700
Data Index: 4047666 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0561. Min Range: -9.0561
Max Act: 8.9936. Min Act: -0.1700
Data Index: 6570875 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0561. Min Range: -9.0561
Max Act: 8.9936. Min Act: -0.1700
Data Index: 2542250 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0561. Min Range: -9.0561
Max Act: 9.0561. Min Act: -0.1700
Data Index: 4527761 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0561. Min Range: -9.0561
Max Act: 8.8686. Min Act: -0.1700
Data Index: 1749119 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0561. Min Range: -9.0561
Max Act: 8.8686. Min Act: -0.1700
Data Index: 6477411 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0561. Min Range: -9.0561
Max Act: 8.8061. Min Act: -0.1700
Data Index: 8390951 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0561. Min Range: -9.0561
Max Act: 8.8061. Min Act: -0.1700
Data Index: 8072135 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0561. Min Range: -9.0561
Max Act: 8.8061. Min Act: -0.1700
Data Index: 4330045 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0561. Min Range: -9.0561
Max Act: 8.6811. Min Act: -0.1700
Data Index: 4181914 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0561. Min Range: -9.0561
Max Act: 8.7436. Min Act: -0.1700
Data Index: 1955786 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0561. Min Range: -9.0561
Max Act: 8.7436. Min Act: -0.1700
Data Index: 7269537 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0561. Min Range: -9.0561
Max Act: 8.7436. Min Act: -0.1700
Data Index: 5399372 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0561. Min Range: -9.0561
Max Act: 8.8061. Min Act: -0.1700
Data Index: 4330040 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0561. Min Range: -9.0561
Max Act: 8.7436. Min Act: -0.1700
Data Index: 1433856 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0561. Min Range: -9.0561
Max Act: 8.7436. Min Act: -0.1700
Data Index: 556951 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0561. Min Range: -9.0561
Max Act: 8.7436. Min Act: -0.1700
Data Index: 5757716 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0561. Min Range: -9.0561
Max Act: 8.7436. Min Act: -0.1700
Data Index: 5707182 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19