Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1768 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1018. Min Range: -6.1018
Max Act: 6.1018. Min Act: -0.1700
Data Index: 223247 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1018. Min Range: -6.1018
Max Act: 5.9768. Min Act: -0.1700
Data Index: 1103530 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1018. Min Range: -6.1018
Max Act: 6.0080. Min Act: -0.1700
Data Index: 7363791 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1018. Min Range: -6.1018
Max Act: 5.9143. Min Act: -0.1700
Data Index: 7292621 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1018. Min Range: -6.1018
Max Act: 5.8830. Min Act: -0.1700
Data Index: 1607551 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1018. Min Range: -6.1018
Max Act: 5.8518. Min Act: -0.1700
Data Index: 3608717 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1018. Min Range: -6.1018
Max Act: 5.8205. Min Act: -0.1700
Data Index: 6924971 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1018. Min Range: -6.1018
Max Act: 5.8205. Min Act: -0.1700
Data Index: 2182250 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1018. Min Range: -6.1018
Max Act: 5.8205. Min Act: -0.1700
Data Index: 588633 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1018. Min Range: -6.1018
Max Act: 5.7893. Min Act: -0.1700
Data Index: 7955581 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1018. Min Range: -6.1018
Max Act: 5.7893. Min Act: -0.1700
Data Index: 2888236 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1018. Min Range: -6.1018
Max Act: 5.8205. Min Act: -0.1700
Data Index: 6996427 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1018. Min Range: -6.1018
Max Act: 5.7893. Min Act: -0.1700
Data Index: 2538492 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1018. Min Range: -6.1018
Max Act: 5.7893. Min Act: -0.1700
Data Index: 8164378 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1018. Min Range: -6.1018
Max Act: 5.7268. Min Act: -0.1700
Data Index: 2647353 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1018. Min Range: -6.1018
Max Act: 5.7268. Min Act: -0.1700
Data Index: 4764205 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1018. Min Range: -6.1018
Max Act: 5.7580. Min Act: -0.1700
Data Index: 6983529 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1018. Min Range: -6.1018
Max Act: 5.7268. Min Act: -0.1700
Data Index: 8230974 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1018. Min Range: -6.1018
Max Act: 5.6955. Min Act: -0.1700
Data Index: 1408508 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1018. Min Range: -6.1018
Max Act: 5.6330. Min Act: -0.1700
Data Index: 5812673 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19