Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4917 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4466. Min Range: -6.4466
Max Act: 6.4466. Min Act: -0.1700
Data Index: 6201752 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4466. Min Range: -6.4466
Max Act: 6.3529. Min Act: -0.1700
Data Index: 680621 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4466. Min Range: -6.4466
Max Act: 6.2904. Min Act: -0.1700
Data Index: 2055719 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4466. Min Range: -6.4466
Max Act: 6.1966. Min Act: -0.1700
Data Index: 5462958 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4466. Min Range: -6.4466
Max Act: 6.1341. Min Act: -0.1700
Data Index: 8439007 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4466. Min Range: -6.4466
Max Act: 6.1341. Min Act: -0.1700
Data Index: 4876692 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4466. Min Range: -6.4466
Max Act: 6.0404. Min Act: -0.1700
Data Index: 1387890 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4466. Min Range: -6.4466
Max Act: 5.9466. Min Act: -0.1700
Data Index: 7354539 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4466. Min Range: -6.4466
Max Act: 5.9154. Min Act: -0.1700
Data Index: 7278072 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4466. Min Range: -6.4466
Max Act: 5.9154. Min Act: -0.1700
Data Index: 5742979 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4466. Min Range: -6.4466
Max Act: 5.9466. Min Act: -0.1700
Data Index: 6672601 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4466. Min Range: -6.4466
Max Act: 5.8841. Min Act: -0.1700
Data Index: 7143501 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4466. Min Range: -6.4466
Max Act: 5.8841. Min Act: -0.1700
Data Index: 2306858 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4466. Min Range: -6.4466
Max Act: 5.8529. Min Act: -0.1700
Data Index: 7331085 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4466. Min Range: -6.4466
Max Act: 5.8529. Min Act: -0.1700
Data Index: 606848 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4466. Min Range: -6.4466
Max Act: 5.8529. Min Act: -0.1700
Data Index: 3669904 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4466. Min Range: -6.4466
Max Act: 5.8529. Min Act: -0.1700
Data Index: 6723150 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4466. Min Range: -6.4466
Max Act: 5.8529. Min Act: -0.1700
Data Index: 5844671 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4466. Min Range: -6.4466
Max Act: 5.8529. Min Act: -0.1700
Data Index: 5274845 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4466. Min Range: -6.4466
Max Act: 5.8216. Min Act: -0.1700
Data Index: 1854440 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19