Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6126 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1073. Min Range: -6.1073
Max Act: 6.1073. Min Act: -0.1700
Data Index: 5328920 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1073. Min Range: -6.1073
Max Act: 6.0136. Min Act: -0.1700
Data Index: 7404827 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1073. Min Range: -6.1073
Max Act: 5.9823. Min Act: -0.1700
Data Index: 3767516 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1073. Min Range: -6.1073
Max Act: 6.0136. Min Act: -0.1700
Data Index: 8079007 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1073. Min Range: -6.1073
Max Act: 5.8886. Min Act: -0.1700
Data Index: 4476184 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1073. Min Range: -6.1073
Max Act: 5.8261. Min Act: -0.1700
Data Index: 5077570 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1073. Min Range: -6.1073
Max Act: 5.7948. Min Act: -0.1700
Data Index: 6464701 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1073. Min Range: -6.1073
Max Act: 5.7948. Min Act: -0.1700
Data Index: 5979750 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1073. Min Range: -6.1073
Max Act: 5.7323. Min Act: -0.1700
Data Index: 2101300 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1073. Min Range: -6.1073
Max Act: 5.7636. Min Act: -0.1700
Data Index: 5365761 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1073. Min Range: -6.1073
Max Act: 5.7011. Min Act: -0.1700
Data Index: 6254162 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1073. Min Range: -6.1073
Max Act: 5.6698. Min Act: -0.1700
Data Index: 7140234 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1073. Min Range: -6.1073
Max Act: 5.6698. Min Act: -0.1700
Data Index: 4348651 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1073. Min Range: -6.1073
Max Act: 5.6698. Min Act: -0.1700
Data Index: 5994419 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1073. Min Range: -6.1073
Max Act: 5.6698. Min Act: -0.1700
Data Index: 5876328 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1073. Min Range: -6.1073
Max Act: 5.6386. Min Act: -0.1700
Data Index: 2540061 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1073. Min Range: -6.1073
Max Act: 5.6386. Min Act: -0.1700
Data Index: 1772829 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1073. Min Range: -6.1073
Max Act: 5.6386. Min Act: -0.1700
Data Index: 807189 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1073. Min Range: -6.1073
Max Act: 5.6073. Min Act: -0.1700
Data Index: 8638472 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1073. Min Range: -6.1073
Max Act: 5.6386. Min Act: -0.1700
Data Index: 5123837 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19