Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4485. Min Range: -6.4485
Max Act: 6.4485. Min Act: -0.1700
Data Index: 3882374 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4485. Min Range: -6.4485
Max Act: 6.3548. Min Act: -0.1700
Data Index: 8471108 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4485. Min Range: -6.4485
Max Act: 6.2923. Min Act: -0.1700
Data Index: 1388257 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4485. Min Range: -6.4485
Max Act: 6.2610. Min Act: -0.1700
Data Index: 4138246 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4485. Min Range: -6.4485
Max Act: 6.1673. Min Act: -0.1700
Data Index: 3222906 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4485. Min Range: -6.4485
Max Act: 6.1360. Min Act: -0.1700
Data Index: 7718536 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4485. Min Range: -6.4485
Max Act: 6.1048. Min Act: -0.1700
Data Index: 3786044 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4485. Min Range: -6.4485
Max Act: 6.1048. Min Act: -0.1700
Data Index: 3547799 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4485. Min Range: -6.4485
Max Act: 6.1048. Min Act: -0.1700
Data Index: 7355105 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4485. Min Range: -6.4485
Max Act: 6.1048. Min Act: -0.1700
Data Index: 3920417 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4485. Min Range: -6.4485
Max Act: 6.0735. Min Act: -0.1700
Data Index: 7660957 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4485. Min Range: -6.4485
Max Act: 6.0110. Min Act: -0.1700
Data Index: 2795192 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4485. Min Range: -6.4485
Max Act: 6.0110. Min Act: -0.1700
Data Index: 4056637 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4485. Min Range: -6.4485
Max Act: 6.0110. Min Act: -0.1700
Data Index: 3108939 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4485. Min Range: -6.4485
Max Act: 5.9798. Min Act: -0.1700
Data Index: 6852043 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4485. Min Range: -6.4485
Max Act: 5.9485. Min Act: -0.1700
Data Index: 1830497 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4485. Min Range: -6.4485
Max Act: 5.9485. Min Act: -0.1700
Data Index: 7252885 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4485. Min Range: -6.4485
Max Act: 5.9485. Min Act: -0.1700
Data Index: 3795852 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4485. Min Range: -6.4485
Max Act: 5.9485. Min Act: -0.1700
Data Index: 7462515 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4485. Min Range: -6.4485
Max Act: 5.9485. Min Act: -0.1700
Data Index: 5767859 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19