Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4128 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9982. Min Range: -6.9982
Max Act: 6.9982. Min Act: -0.1700
Data Index: 8114066 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9982. Min Range: -6.9982
Max Act: 6.4044. Min Act: -0.1700
Data Index: 8807237 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9982. Min Range: -6.9982
Max Act: 6.1857. Min Act: -0.1700
Data Index: 3914748 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9982. Min Range: -6.9982
Max Act: 6.1232. Min Act: -0.1700
Data Index: 5728350 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9982. Min Range: -6.9982
Max Act: 6.0607. Min Act: -0.1700
Data Index: 7994884 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9982. Min Range: -6.9982
Max Act: 6.0919. Min Act: -0.1700
Data Index: 7646598 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9982. Min Range: -6.9982
Max Act: 6.0607. Min Act: -0.1700
Data Index: 3147924 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9982. Min Range: -6.9982
Max Act: 6.0607. Min Act: -0.1700
Data Index: 1397054 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9982. Min Range: -6.9982
Max Act: 6.0294. Min Act: -0.1700
Data Index: 5616840 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9982. Min Range: -6.9982
Max Act: 6.0607. Min Act: -0.1700
Data Index: 4511048 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9982. Min Range: -6.9982
Max Act: 6.0294. Min Act: -0.1700
Data Index: 4470056 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9982. Min Range: -6.9982
Max Act: 6.0294. Min Act: -0.1700
Data Index: 1363589 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9982. Min Range: -6.9982
Max Act: 5.9669. Min Act: -0.1700
Data Index: 2100360 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9982. Min Range: -6.9982
Max Act: 5.9357. Min Act: -0.1700
Data Index: 5059840 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9982. Min Range: -6.9982
Max Act: 5.9357. Min Act: -0.1700
Data Index: 6666233 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9982. Min Range: -6.9982
Max Act: 5.9357. Min Act: -0.1700
Data Index: 6348022 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9982. Min Range: -6.9982
Max Act: 5.9357. Min Act: -0.1700
Data Index: 6160273 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9982. Min Range: -6.9982
Max Act: 5.9044. Min Act: -0.1700
Data Index: 2752950 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9982. Min Range: -6.9982
Max Act: 5.9044. Min Act: -0.1700
Data Index: 3150396 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9982. Min Range: -6.9982
Max Act: 5.8732. Min Act: -0.1700
Data Index: 5143932 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19