Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6090 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6090. Min Range: -9.6090
Max Act: 9.6090. Min Act: -0.1700
Data Index: 859359 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6090. Min Range: -9.6090
Max Act: 9.4840. Min Act: -0.1700
Data Index: 859352 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6090. Min Range: -9.6090
Max Act: 9.4215. Min Act: -0.1700
Data Index: 859356 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6090. Min Range: -9.6090
Max Act: 9.4215. Min Act: -0.1700
Data Index: 859358 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6090. Min Range: -9.6090
Max Act: 9.3590. Min Act: -0.1700
Data Index: 859360 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6090. Min Range: -9.6090
Max Act: 9.2965. Min Act: -0.1700
Data Index: 932384 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6090. Min Range: -9.6090
Max Act: 9.2965. Min Act: -0.1700
Data Index: 3073379 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6090. Min Range: -9.6090
Max Act: 9.2965. Min Act: -0.1700
Data Index: 1860673 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6090. Min Range: -9.6090
Max Act: 9.0465. Min Act: -0.1700
Data Index: 8083389 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6090. Min Range: -9.6090
Max Act: 9.1090. Min Act: -0.1700
Data Index: 3117448 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6090. Min Range: -9.6090
Max Act: 8.9840. Min Act: -0.1700
Data Index: 695563 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6090. Min Range: -9.6090
Max Act: 8.9840. Min Act: -0.1700
Data Index: 5334996 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6090. Min Range: -9.6090
Max Act: 8.9840. Min Act: -0.1700
Data Index: 1290524 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6090. Min Range: -9.6090
Max Act: 8.9215. Min Act: -0.1700
Data Index: 859348 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6090. Min Range: -9.6090
Max Act: 8.9215. Min Act: -0.1700
Data Index: 3091139 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6090. Min Range: -9.6090
Max Act: 8.8590. Min Act: -0.1700
Data Index: 4995091 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6090. Min Range: -9.6090
Max Act: 8.7965. Min Act: -0.1700
Data Index: 1462264 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6090. Min Range: -9.6090
Max Act: 8.7965. Min Act: -0.1700
Data Index: 1438899 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6090. Min Range: -9.6090
Max Act: 8.7965. Min Act: -0.1700
Data Index: 1277991 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6090. Min Range: -9.6090
Max Act: 8.7965. Min Act: -0.1700
Data Index: 1343664 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19