Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5458 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4052. Min Range: -6.4052
Max Act: 6.4052. Min Act: -0.1700
Data Index: 7141145 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4052. Min Range: -6.4052
Max Act: 6.2489. Min Act: -0.1700
Data Index: 4919549 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4052. Min Range: -6.4052
Max Act: 6.0927. Min Act: -0.1700
Data Index: 7961161 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4052. Min Range: -6.4052
Max Act: 6.0614. Min Act: -0.1700
Data Index: 7512689 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.9989. Min Act: -0.1700
Data Index: 186751 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.9677. Min Act: -0.1700
Data Index: 7657723 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.9364. Min Act: -0.1700
Data Index: 7524019 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.9677. Min Act: -0.1700
Data Index: 6819993 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.9364. Min Act: -0.1700
Data Index: 1110249 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.9364. Min Act: -0.1700
Data Index: 3439658 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.9364. Min Act: -0.1700
Data Index: 3318762 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.9052. Min Act: -0.1700
Data Index: 5627743 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.8739. Min Act: -0.1700
Data Index: 5976648 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.8427. Min Act: -0.1700
Data Index: 7800813 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.8427. Min Act: -0.1700
Data Index: 759609 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.8114. Min Act: -0.1700
Data Index: 2294776 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.8427. Min Act: -0.1700
Data Index: 7212596 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.8114. Min Act: -0.1700
Data Index: 7494164 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.8114. Min Act: -0.1700
Data Index: 679092 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.7489. Min Act: -0.1700
Data Index: 7467400 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19