Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3721 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9300. Min Range: -5.9300
Max Act: 5.9300. Min Act: -0.1700
Data Index: 3396013 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9300. Min Range: -5.9300
Max Act: 5.8987. Min Act: -0.1700
Data Index: 5837585 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9300. Min Range: -5.9300
Max Act: 5.8675. Min Act: -0.1700
Data Index: 3390094 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9300. Min Range: -5.9300
Max Act: 5.8362. Min Act: -0.1700
Data Index: 2101730 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9300. Min Range: -5.9300
Max Act: 5.8050. Min Act: -0.1700
Data Index: 3488539 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9300. Min Range: -5.9300
Max Act: 5.8050. Min Act: -0.1700
Data Index: 4600239 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9300. Min Range: -5.9300
Max Act: 5.7737. Min Act: -0.1700
Data Index: 4756528 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9300. Min Range: -5.9300
Max Act: 5.7737. Min Act: -0.1700
Data Index: 430423 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9300. Min Range: -5.9300
Max Act: 5.7737. Min Act: -0.1700
Data Index: 8535779 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9300. Min Range: -5.9300
Max Act: 5.7737. Min Act: -0.1700
Data Index: 4176065 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9300. Min Range: -5.9300
Max Act: 5.7425. Min Act: -0.1700
Data Index: 4115656 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9300. Min Range: -5.9300
Max Act: 5.7737. Min Act: -0.1700
Data Index: 2917001 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9300. Min Range: -5.9300
Max Act: 5.7737. Min Act: -0.1700
Data Index: 1391252 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9300. Min Range: -5.9300
Max Act: 5.7737. Min Act: -0.1700
Data Index: 6757667 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9300. Min Range: -5.9300
Max Act: 5.7737. Min Act: -0.1700
Data Index: 2180038 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9300. Min Range: -5.9300
Max Act: 5.7425. Min Act: -0.1700
Data Index: 5604238 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9300. Min Range: -5.9300
Max Act: 5.7425. Min Act: -0.1700
Data Index: 6623492 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9300. Min Range: -5.9300
Max Act: 5.7425. Min Act: -0.1700
Data Index: 293542 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9300. Min Range: -5.9300
Max Act: 5.7425. Min Act: -0.1700
Data Index: 7895670 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9300. Min Range: -5.9300
Max Act: 5.7425. Min Act: -0.1700
Data Index: 8505335 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19