Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2123 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5669. Min Range: -4.5669
Max Act: 4.5669. Min Act: -0.1700
Data Index: 518629 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5669. Min Range: -4.5669
Max Act: 4.5357. Min Act: -0.1700
Data Index: 5305655 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5669. Min Range: -4.5669
Max Act: 4.5044. Min Act: -0.1700
Data Index: 5437990 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5669. Min Range: -4.5669
Max Act: 4.4732. Min Act: -0.1700
Data Index: 7596803 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5669. Min Range: -4.5669
Max Act: 4.4732. Min Act: -0.1700
Data Index: 1792000 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5669. Min Range: -4.5669
Max Act: 4.4419. Min Act: -0.1700
Data Index: 4264528 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5669. Min Range: -4.5669
Max Act: 4.4419. Min Act: -0.1700
Data Index: 6091341 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5669. Min Range: -4.5669
Max Act: 4.4419. Min Act: -0.1700
Data Index: 7100916 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5669. Min Range: -4.5669
Max Act: 4.3482. Min Act: -0.1700
Data Index: 79057 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5669. Min Range: -4.5669
Max Act: 4.3794. Min Act: -0.1700
Data Index: 150136 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5669. Min Range: -4.5669
Max Act: 4.3482. Min Act: -0.1700
Data Index: 227682 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5669. Min Range: -4.5669
Max Act: 4.3794. Min Act: -0.1700
Data Index: 3010188 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5669. Min Range: -4.5669
Max Act: 4.3482. Min Act: -0.1700
Data Index: 4932146 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5669. Min Range: -4.5669
Max Act: 4.3482. Min Act: -0.1700
Data Index: 3453160 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5669. Min Range: -4.5669
Max Act: 4.3169. Min Act: -0.1700
Data Index: 3495408 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5669. Min Range: -4.5669
Max Act: 4.3169. Min Act: -0.1700
Data Index: 1871870 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5669. Min Range: -4.5669
Max Act: 4.3482. Min Act: -0.1700
Data Index: 7796542 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5669. Min Range: -4.5669
Max Act: 4.3169. Min Act: -0.1700
Data Index: 1297415 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5669. Min Range: -4.5669
Max Act: 4.3169. Min Act: -0.1700
Data Index: 2688624 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5669. Min Range: -4.5669
Max Act: 4.3169. Min Act: -0.1700
Data Index: 7079401 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19