Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2033 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2527. Min Range: -5.2527
Max Act: 5.2527. Min Act: -0.1700
Data Index: 2838945 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2527. Min Range: -5.2527
Max Act: 5.2214. Min Act: -0.1700
Data Index: 7509145 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2527. Min Range: -5.2527
Max Act: 5.1902. Min Act: -0.1700
Data Index: 1063878 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2527. Min Range: -5.2527
Max Act: 5.1589. Min Act: -0.1700
Data Index: 3514996 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2527. Min Range: -5.2527
Max Act: 5.1589. Min Act: -0.1700
Data Index: 3632418 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2527. Min Range: -5.2527
Max Act: 5.1277. Min Act: -0.1700
Data Index: 7623608 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2527. Min Range: -5.2527
Max Act: 5.0964. Min Act: -0.1700
Data Index: 6641540 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2527. Min Range: -5.2527
Max Act: 5.0964. Min Act: -0.1700
Data Index: 2141247 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2527. Min Range: -5.2527
Max Act: 5.0964. Min Act: -0.1700
Data Index: 7399972 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2527. Min Range: -5.2527
Max Act: 5.0964. Min Act: -0.1700
Data Index: 2675631 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2527. Min Range: -5.2527
Max Act: 5.0652. Min Act: -0.1700
Data Index: 8688076 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2527. Min Range: -5.2527
Max Act: 5.0652. Min Act: -0.1700
Data Index: 4151905 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2527. Min Range: -5.2527
Max Act: 5.0652. Min Act: -0.1700
Data Index: 8505110 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2527. Min Range: -5.2527
Max Act: 5.0339. Min Act: -0.1700
Data Index: 6181218 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2527. Min Range: -5.2527
Max Act: 5.0339. Min Act: -0.1700
Data Index: 6793951 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2527. Min Range: -5.2527
Max Act: 5.0339. Min Act: -0.1700
Data Index: 5639403 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2527. Min Range: -5.2527
Max Act: 5.0027. Min Act: -0.1700
Data Index: 6476461 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2527. Min Range: -5.2527
Max Act: 5.0027. Min Act: -0.1700
Data Index: 6489444 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2527. Min Range: -5.2527
Max Act: 4.9714. Min Act: -0.1700
Data Index: 4186491 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2527. Min Range: -5.2527
Max Act: 5.0027. Min Act: -0.1700
Data Index: 3384196 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19