Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1087 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2728. Min Range: -10.2728
Max Act: 10.2728. Min Act: -0.1700
Data Index: 4919482 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2728. Min Range: -10.2728
Max Act: 10.2103. Min Act: -0.1700
Data Index: 144923 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2728. Min Range: -10.2728
Max Act: 10.2103. Min Act: -0.1700
Data Index: 2752435 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2728. Min Range: -10.2728
Max Act: 10.2103. Min Act: -0.1700
Data Index: 8108675 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2728. Min Range: -10.2728
Max Act: 10.1478. Min Act: -0.1700
Data Index: 3242735 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2728. Min Range: -10.2728
Max Act: 10.0228. Min Act: -0.1700
Data Index: 7006712 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2728. Min Range: -10.2728
Max Act: 10.0228. Min Act: -0.1700
Data Index: 4723402 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2728. Min Range: -10.2728
Max Act: 9.9603. Min Act: -0.1700
Data Index: 7278268 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2728. Min Range: -10.2728
Max Act: 9.9603. Min Act: -0.1700
Data Index: 4982800 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2728. Min Range: -10.2728
Max Act: 9.9603. Min Act: -0.1700
Data Index: 13651 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2728. Min Range: -10.2728
Max Act: 9.8978. Min Act: -0.1700
Data Index: 909679 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2728. Min Range: -10.2728
Max Act: 9.7728. Min Act: -0.1700
Data Index: 8013896 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2728. Min Range: -10.2728
Max Act: 9.7728. Min Act: -0.1700
Data Index: 6684751 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2728. Min Range: -10.2728
Max Act: 9.7728. Min Act: -0.1700
Data Index: 5816734 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2728. Min Range: -10.2728
Max Act: 9.7103. Min Act: -0.1700
Data Index: 1509600 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2728. Min Range: -10.2728
Max Act: 9.6478. Min Act: -0.1700
Data Index: 3903957 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2728. Min Range: -10.2728
Max Act: 9.6478. Min Act: -0.1700
Data Index: 4117744 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2728. Min Range: -10.2728
Max Act: 9.6478. Min Act: -0.1700
Data Index: 4574893 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2728. Min Range: -10.2728
Max Act: 9.5853. Min Act: -0.1700
Data Index: 4590382 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2728. Min Range: -10.2728
Max Act: 9.5853. Min Act: -0.1700
Data Index: 5117715 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19