Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3268 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.6397. Min Act: -0.1700
Data Index: 3163627 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.5772. Min Act: -0.1700
Data Index: 6123040 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.4522. Min Act: -0.1700
Data Index: 2755142 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.3897. Min Act: -0.1700
Data Index: 2280797 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.3272. Min Act: -0.1700
Data Index: 1468009 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.2647. Min Act: -0.1700
Data Index: 4682597 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.3272. Min Act: -0.1700
Data Index: 2673568 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.2647. Min Act: -0.1700
Data Index: 419034 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.1397. Min Act: -0.1699
Data Index: 3054806 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.2022. Min Act: -0.1700
Data Index: 2050145 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.2022. Min Act: -0.1700
Data Index: 931031 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.1397. Min Act: -0.1699
Data Index: 5939616 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.2022. Min Act: -0.1700
Data Index: 3215787 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.2022. Min Act: -0.1700
Data Index: 2270748 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.2022. Min Act: -0.1700
Data Index: 7821282 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.1397. Min Act: -0.1700
Data Index: 4109024 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.1397. Min Act: -0.1700
Data Index: 1203652 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.1397. Min Act: -0.1700
Data Index: 4968004 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.1397. Min Act: -0.1700
Data Index: 4211803 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.1397. Min Act: -0.1700
Data Index: 1594376 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #19