Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6015 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6596. Min Range: -4.6596
Max Act: 4.6596. Min Act: -0.1700
Data Index: 4841242 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6596. Min Range: -4.6596
Max Act: 4.4721. Min Act: -0.1700
Data Index: 3977574 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6596. Min Range: -4.6596
Max Act: 4.4096. Min Act: -0.1700
Data Index: 8775898 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6596. Min Range: -4.6596
Max Act: 4.4096. Min Act: -0.1700
Data Index: 1712900 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6596. Min Range: -4.6596
Max Act: 4.3159. Min Act: -0.1700
Data Index: 696061 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6596. Min Range: -4.6596
Max Act: 4.3159. Min Act: -0.1700
Data Index: 8052084 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6596. Min Range: -4.6596
Max Act: 4.2534. Min Act: -0.1700
Data Index: 5202609 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6596. Min Range: -4.6596
Max Act: 4.2846. Min Act: -0.1700
Data Index: 5908326 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6596. Min Range: -4.6596
Max Act: 4.2221. Min Act: -0.1700
Data Index: 512507 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6596. Min Range: -4.6596
Max Act: 4.2221. Min Act: -0.1700
Data Index: 1322460 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6596. Min Range: -4.6596
Max Act: 4.1909. Min Act: -0.1700
Data Index: 3031777 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6596. Min Range: -4.6596
Max Act: 4.2221. Min Act: -0.1700
Data Index: 4702660 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6596. Min Range: -4.6596
Max Act: 4.1909. Min Act: -0.1700
Data Index: 382217 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6596. Min Range: -4.6596
Max Act: 4.1909. Min Act: -0.1700
Data Index: 3293170 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6596. Min Range: -4.6596
Max Act: 4.1596. Min Act: -0.1700
Data Index: 1312030 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6596. Min Range: -4.6596
Max Act: 4.1596. Min Act: -0.1700
Data Index: 5539546 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6596. Min Range: -4.6596
Max Act: 4.1596. Min Act: -0.1700
Data Index: 1605684 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6596. Min Range: -4.6596
Max Act: 4.1596. Min Act: -0.1700
Data Index: 6149550 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6596. Min Range: -4.6596
Max Act: 4.1596. Min Act: -0.1700
Data Index: 6420830 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6596. Min Range: -4.6596
Max Act: 4.1596. Min Act: -0.1700
Data Index: 289742 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19