Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1809 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.4707. Min Act: -0.1700
Data Index: 5875656 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.4395. Min Act: -0.1700
Data Index: 3200778 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.0332. Min Act: -0.1700
Data Index: 7233449 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4707. Min Range: -7.4707
Max Act: 6.9707. Min Act: -0.1700
Data Index: 7231759 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4707. Min Range: -7.4707
Max Act: 6.9395. Min Act: -0.1700
Data Index: 2167385 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4707. Min Range: -7.4707
Max Act: 6.9082. Min Act: -0.1700
Data Index: 1636493 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4707. Min Range: -7.4707
Max Act: 6.8770. Min Act: -0.1700
Data Index: 1375765 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4707. Min Range: -7.4707
Max Act: 6.8145. Min Act: -0.1700
Data Index: 7333990 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4707. Min Range: -7.4707
Max Act: 6.8145. Min Act: -0.1700
Data Index: 3551055 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4707. Min Range: -7.4707
Max Act: 6.7832. Min Act: -0.1700
Data Index: 5141578 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4707. Min Range: -7.4707
Max Act: 6.8145. Min Act: -0.1700
Data Index: 6509493 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4707. Min Range: -7.4707
Max Act: 6.7832. Min Act: -0.1700
Data Index: 8362317 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4707. Min Range: -7.4707
Max Act: 6.7832. Min Act: -0.1700
Data Index: 1161077 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4707. Min Range: -7.4707
Max Act: 6.7832. Min Act: -0.1700
Data Index: 677638 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4707. Min Range: -7.4707
Max Act: 6.7832. Min Act: -0.1700
Data Index: 904482 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4707. Min Range: -7.4707
Max Act: 6.7832. Min Act: -0.1700
Data Index: 8017426 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4707. Min Range: -7.4707
Max Act: 6.7520. Min Act: -0.1700
Data Index: 3867831 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4707. Min Range: -7.4707
Max Act: 6.7520. Min Act: -0.1700
Data Index: 6608833 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4707. Min Range: -7.4707
Max Act: 6.7520. Min Act: -0.1700
Data Index: 6964883 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4707. Min Range: -7.4707
Max Act: 6.7520. Min Act: -0.1700
Data Index: 7508408 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19