Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1618 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7644. Min Range: -3.7644
Max Act: 3.7644. Min Act: -0.1700
Data Index: 5470941 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7644. Min Range: -3.7644
Max Act: 3.7644. Min Act: -0.1700
Data Index: 3004444 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7644. Min Range: -3.7644
Max Act: 3.7331. Min Act: -0.1700
Data Index: 8510918 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7644. Min Range: -3.7644
Max Act: 3.7019. Min Act: -0.1700
Data Index: 6601898 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7644. Min Range: -3.7644
Max Act: 3.7019. Min Act: -0.1700
Data Index: 8390920 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7644. Min Range: -3.7644
Max Act: 3.7019. Min Act: -0.1700
Data Index: 877557 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7644. Min Range: -3.7644
Max Act: 3.7019. Min Act: -0.1700
Data Index: 3066439 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7644. Min Range: -3.7644
Max Act: 3.6393. Min Act: -0.1700
Data Index: 6365608 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7644. Min Range: -3.7644
Max Act: 3.6393. Min Act: -0.1700
Data Index: 2801587 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7644. Min Range: -3.7644
Max Act: 3.6706. Min Act: -0.1700
Data Index: 8284146 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7644. Min Range: -3.7644
Max Act: 3.6706. Min Act: -0.1700
Data Index: 3324248 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7644. Min Range: -3.7644
Max Act: 3.6393. Min Act: -0.1700
Data Index: 3254178 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7644. Min Range: -3.7644
Max Act: 3.6393. Min Act: -0.1700
Data Index: 4396739 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7644. Min Range: -3.7644
Max Act: 3.6393. Min Act: -0.1700
Data Index: 2095097 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7644. Min Range: -3.7644
Max Act: 3.6393. Min Act: -0.1700
Data Index: 4733309 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7644. Min Range: -3.7644
Max Act: 3.6393. Min Act: -0.1700
Data Index: 8405465 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7644. Min Range: -3.7644
Max Act: 3.6393. Min Act: -0.1700
Data Index: 7712992 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7644. Min Range: -3.7644
Max Act: 3.6080. Min Act: -0.1700
Data Index: 2330674 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7644. Min Range: -3.7644
Max Act: 3.6080. Min Act: -0.1700
Data Index: 4787237 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7644. Min Range: -3.7644
Max Act: 3.6080. Min Act: -0.1700
Data Index: 5480760 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19