Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 410 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7363. Min Range: -8.7363
Max Act: 8.7363. Min Act: -0.1700
Data Index: 4254677 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7363. Min Range: -8.7363
Max Act: 8.4238. Min Act: -0.1700
Data Index: 6653282 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7363. Min Range: -8.7363
Max Act: 8.2363. Min Act: -0.1700
Data Index: 1794940 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7363. Min Range: -8.7363
Max Act: 7.9863. Min Act: -0.1700
Data Index: 5266959 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7363. Min Range: -8.7363
Max Act: 8.0175. Min Act: -0.1700
Data Index: 3072863 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7363. Min Range: -8.7363
Max Act: 7.9550. Min Act: -0.1700
Data Index: 770647 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7363. Min Range: -8.7363
Max Act: 7.9238. Min Act: -0.1700
Data Index: 8380517 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7363. Min Range: -8.7363
Max Act: 7.8925. Min Act: -0.1700
Data Index: 5200061 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7363. Min Range: -8.7363
Max Act: 7.8925. Min Act: -0.1700
Data Index: 415606 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7363. Min Range: -8.7363
Max Act: 7.8925. Min Act: -0.1700
Data Index: 6001270 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7363. Min Range: -8.7363
Max Act: 7.7988. Min Act: -0.1700
Data Index: 3001803 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7363. Min Range: -8.7363
Max Act: 7.7988. Min Act: -0.1700
Data Index: 1598864 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7363. Min Range: -8.7363
Max Act: 7.7675. Min Act: -0.1700
Data Index: 2647618 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7363. Min Range: -8.7363
Max Act: 7.6738. Min Act: -0.1700
Data Index: 1194014 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7363. Min Range: -8.7363
Max Act: 7.6425. Min Act: -0.1700
Data Index: 1887626 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7363. Min Range: -8.7363
Max Act: 7.6113. Min Act: -0.1700
Data Index: 3079046 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7363. Min Range: -8.7363
Max Act: 7.6113. Min Act: -0.1700
Data Index: 6642971 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7363. Min Range: -8.7363
Max Act: 7.6113. Min Act: -0.1700
Data Index: 2400093 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7363. Min Range: -8.7363
Max Act: 7.5800. Min Act: -0.1700
Data Index: 2197386 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7363. Min Range: -8.7363
Max Act: 7.5488. Min Act: -0.1700
Data Index: 516865 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19