Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2415 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1496. Min Range: -4.1496
Max Act: 4.1496. Min Act: -0.1700
Data Index: 271479 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1496. Min Range: -4.1496
Max Act: 4.0871. Min Act: -0.1700
Data Index: 1548813 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1496. Min Range: -4.1496
Max Act: 4.0871. Min Act: -0.1700
Data Index: 4798293 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1496. Min Range: -4.1496
Max Act: 4.0558. Min Act: -0.1700
Data Index: 2184768 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1496. Min Range: -4.1496
Max Act: 4.0558. Min Act: -0.1700
Data Index: 7647303 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1496. Min Range: -4.1496
Max Act: 4.0558. Min Act: -0.1700
Data Index: 1407206 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1496. Min Range: -4.1496
Max Act: 4.0558. Min Act: -0.1700
Data Index: 6212052 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1496. Min Range: -4.1496
Max Act: 4.0558. Min Act: -0.1700
Data Index: 5480415 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1496. Min Range: -4.1496
Max Act: 4.0558. Min Act: -0.1700
Data Index: 4706449 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1496. Min Range: -4.1496
Max Act: 4.0558. Min Act: -0.1700
Data Index: 4366455 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1496. Min Range: -4.1496
Max Act: 4.0558. Min Act: -0.1700
Data Index: 4331093 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1496. Min Range: -4.1496
Max Act: 4.0558. Min Act: -0.1700
Data Index: 3753787 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1496. Min Range: -4.1496
Max Act: 4.0558. Min Act: -0.1700
Data Index: 794073 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1496. Min Range: -4.1496
Max Act: 4.0558. Min Act: -0.1700
Data Index: 3424718 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1496. Min Range: -4.1496
Max Act: 4.0246. Min Act: -0.1700
Data Index: 1472886 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1496. Min Range: -4.1496
Max Act: 4.0246. Min Act: -0.1700
Data Index: 2577495 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1496. Min Range: -4.1496
Max Act: 4.0246. Min Act: -0.1700
Data Index: 3049267 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1496. Min Range: -4.1496
Max Act: 4.0246. Min Act: -0.1700
Data Index: 3148091 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1496. Min Range: -4.1496
Max Act: 4.0246. Min Act: -0.1700
Data Index: 3300649 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1496. Min Range: -4.1496
Max Act: 4.0246. Min Act: -0.1700
Data Index: 3319170 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19