Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1538 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0985. Min Range: -5.0985
Max Act: 5.0985. Min Act: -0.1700
Data Index: 6205061 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0985. Min Range: -5.0985
Max Act: 4.9110. Min Act: -0.1700
Data Index: 1215214 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0985. Min Range: -5.0985
Max Act: 4.8798. Min Act: -0.1700
Data Index: 5372138 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0985. Min Range: -5.0985
Max Act: 4.8173. Min Act: -0.1700
Data Index: 5036810 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0985. Min Range: -5.0985
Max Act: 4.7860. Min Act: -0.1700
Data Index: 8165333 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0985. Min Range: -5.0985
Max Act: 4.7860. Min Act: -0.1700
Data Index: 4656687 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0985. Min Range: -5.0985
Max Act: 4.7860. Min Act: -0.1700
Data Index: 8723095 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0985. Min Range: -5.0985
Max Act: 4.7548. Min Act: -0.1700
Data Index: 117749 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0985. Min Range: -5.0985
Max Act: 4.7548. Min Act: -0.1700
Data Index: 117743 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0985. Min Range: -5.0985
Max Act: 4.7860. Min Act: -0.1700
Data Index: 6416162 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0985. Min Range: -5.0985
Max Act: 4.7548. Min Act: -0.1700
Data Index: 4108139 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0985. Min Range: -5.0985
Max Act: 4.7548. Min Act: -0.1700
Data Index: 3805449 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0985. Min Range: -5.0985
Max Act: 4.7235. Min Act: -0.1700
Data Index: 6380395 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0985. Min Range: -5.0985
Max Act: 4.7235. Min Act: -0.1700
Data Index: 3267717 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0985. Min Range: -5.0985
Max Act: 4.7235. Min Act: -0.1700
Data Index: 3861765 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0985. Min Range: -5.0985
Max Act: 4.7235. Min Act: -0.1700
Data Index: 8045560 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0985. Min Range: -5.0985
Max Act: 4.6923. Min Act: -0.1700
Data Index: 6269781 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0985. Min Range: -5.0985
Max Act: 4.6923. Min Act: -0.1700
Data Index: 2449170 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0985. Min Range: -5.0985
Max Act: 4.6923. Min Act: -0.1700
Data Index: 2757231 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0985. Min Range: -5.0985
Max Act: 4.6923. Min Act: -0.1700
Data Index: 1963888 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19