Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2568 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6705. Min Range: -5.6705
Max Act: 5.6705. Min Act: -0.1700
Data Index: 1631622 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6705. Min Range: -5.6705
Max Act: 5.5142. Min Act: -0.1700
Data Index: 1508898 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6705. Min Range: -5.6705
Max Act: 5.4830. Min Act: -0.1700
Data Index: 3228528 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6705. Min Range: -5.6705
Max Act: 5.4830. Min Act: -0.1700
Data Index: 3559203 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6705. Min Range: -5.6705
Max Act: 5.4517. Min Act: -0.1700
Data Index: 6571674 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6705. Min Range: -5.6705
Max Act: 5.4517. Min Act: -0.1700
Data Index: 5739102 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6705. Min Range: -5.6705
Max Act: 5.3892. Min Act: -0.1700
Data Index: 7575561 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6705. Min Range: -5.6705
Max Act: 5.3892. Min Act: -0.1700
Data Index: 6468563 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6705. Min Range: -5.6705
Max Act: 5.3580. Min Act: -0.1700
Data Index: 1409066 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6705. Min Range: -5.6705
Max Act: 5.3580. Min Act: -0.1700
Data Index: 3252801 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6705. Min Range: -5.6705
Max Act: 5.3580. Min Act: -0.1700
Data Index: 3978773 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6705. Min Range: -5.6705
Max Act: 5.3267. Min Act: -0.1700
Data Index: 6253171 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6705. Min Range: -5.6705
Max Act: 5.3267. Min Act: -0.1700
Data Index: 3803444 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6705. Min Range: -5.6705
Max Act: 5.3267. Min Act: -0.1700
Data Index: 1985929 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6705. Min Range: -5.6705
Max Act: 5.3267. Min Act: -0.1700
Data Index: 3117641 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6705. Min Range: -5.6705
Max Act: 5.2955. Min Act: -0.1700
Data Index: 4436423 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6705. Min Range: -5.6705
Max Act: 5.2955. Min Act: -0.1700
Data Index: 3791757 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6705. Min Range: -5.6705
Max Act: 5.2955. Min Act: -0.1700
Data Index: 3107115 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6705. Min Range: -5.6705
Max Act: 5.2955. Min Act: -0.1700
Data Index: 2619222 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6705. Min Range: -5.6705
Max Act: 5.2955. Min Act: -0.1700
Data Index: 5104170 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19