Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3113 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5219. Min Range: -8.5219
Max Act: 8.5219. Min Act: -0.1700
Data Index: 6089631 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5219. Min Range: -8.5219
Max Act: 7.7407. Min Act: -0.1700
Data Index: 7548111 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5219. Min Range: -8.5219
Max Act: 7.6157. Min Act: -0.1700
Data Index: 8053071 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5219. Min Range: -8.5219
Max Act: 7.5532. Min Act: -0.1700
Data Index: 1682068 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5219. Min Range: -8.5219
Max Act: 7.3969. Min Act: -0.1700
Data Index: 7348683 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5219. Min Range: -8.5219
Max Act: 7.3657. Min Act: -0.1700
Data Index: 652885 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5219. Min Range: -8.5219
Max Act: 7.3969. Min Act: -0.1700
Data Index: 7302356 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5219. Min Range: -8.5219
Max Act: 7.3344. Min Act: -0.1700
Data Index: 6941361 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5219. Min Range: -8.5219
Max Act: 7.3657. Min Act: -0.1700
Data Index: 8188975 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5219. Min Range: -8.5219
Max Act: 7.3032. Min Act: -0.1700
Data Index: 3046892 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5219. Min Range: -8.5219
Max Act: 7.3032. Min Act: -0.1700
Data Index: 991071 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5219. Min Range: -8.5219
Max Act: 7.2407. Min Act: -0.1700
Data Index: 4515105 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5219. Min Range: -8.5219
Max Act: 7.2407. Min Act: -0.1700
Data Index: 4177722 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5219. Min Range: -8.5219
Max Act: 7.2719. Min Act: -0.1700
Data Index: 3737564 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5219. Min Range: -8.5219
Max Act: 7.2094. Min Act: -0.1700
Data Index: 7819237 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5219. Min Range: -8.5219
Max Act: 7.1469. Min Act: -0.1700
Data Index: 6383674 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5219. Min Range: -8.5219
Max Act: 7.1469. Min Act: -0.1700
Data Index: 1101052 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5219. Min Range: -8.5219
Max Act: 7.1469. Min Act: -0.1700
Data Index: 6142649 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5219. Min Range: -8.5219
Max Act: 7.1157. Min Act: -0.1700
Data Index: 2509024 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5219. Min Range: -8.5219
Max Act: 7.1157. Min Act: -0.1700
Data Index: 4070640 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19