Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5102 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2338. Min Range: -3.2338
Max Act: 3.2338. Min Act: -0.1700
Data Index: 5197529 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2338. Min Range: -3.2338
Max Act: 3.2023. Min Act: -0.1700
Data Index: 1081714 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2338. Min Range: -3.2338
Max Act: 3.1709. Min Act: -0.1700
Data Index: 3227723 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2338. Min Range: -3.2338
Max Act: 3.1394. Min Act: -0.1700
Data Index: 6818179 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2338. Min Range: -3.2338
Max Act: 3.1394. Min Act: -0.1700
Data Index: 4975211 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2338. Min Range: -3.2338
Max Act: 3.1394. Min Act: -0.1700
Data Index: 480638 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2338. Min Range: -3.2338
Max Act: 3.1079. Min Act: -0.1700
Data Index: 1531213 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2338. Min Range: -3.2338
Max Act: 3.1394. Min Act: -0.1700
Data Index: 5542688 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2338. Min Range: -3.2338
Max Act: 3.1394. Min Act: -0.1700
Data Index: 5902920 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2338. Min Range: -3.2338
Max Act: 3.1079. Min Act: -0.1700
Data Index: 5626100 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2338. Min Range: -3.2338
Max Act: 3.1079. Min Act: -0.1700
Data Index: 8061340 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2338. Min Range: -3.2338
Max Act: 3.0764. Min Act: -0.1700
Data Index: 1476243 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2338. Min Range: -3.2338
Max Act: 3.1079. Min Act: -0.1700
Data Index: 7673683 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2338. Min Range: -3.2338
Max Act: 3.1079. Min Act: -0.1700
Data Index: 6263118 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2338. Min Range: -3.2338
Max Act: 3.1079. Min Act: -0.1700
Data Index: 1101454 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2338. Min Range: -3.2338
Max Act: 3.1079. Min Act: -0.1700
Data Index: 7008147 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2338. Min Range: -3.2338
Max Act: 3.0764. Min Act: -0.1700
Data Index: 3319016 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2338. Min Range: -3.2338
Max Act: 3.0448. Min Act: -0.1700
Data Index: 5906191 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2338. Min Range: -3.2338
Max Act: 3.0764. Min Act: -0.1700
Data Index: 5035087 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2338. Min Range: -3.2338
Max Act: 3.0764. Min Act: -0.1700
Data Index: 6102255 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19