Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 813 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4495. Min Range: -3.4495
Max Act: 3.4495. Min Act: -0.1700
Data Index: 2568693 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4495. Min Range: -3.4495
Max Act: 3.2455. Min Act: -0.1700
Data Index: 2568694 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4495. Min Range: -3.4495
Max Act: 3.1669. Min Act: -0.1700
Data Index: 1882062 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4495. Min Range: -3.4495
Max Act: 3.1669. Min Act: -0.1700
Data Index: 3028619 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4495. Min Range: -3.4495
Max Act: 3.1354. Min Act: -0.1700
Data Index: 4709725 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4495. Min Range: -3.4495
Max Act: 3.1354. Min Act: -0.1700
Data Index: 8052807 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4495. Min Range: -3.4495
Max Act: 3.1354. Min Act: -0.1700
Data Index: 4810081 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4495. Min Range: -3.4495
Max Act: 3.1039. Min Act: -0.1700
Data Index: 4416802 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4495. Min Range: -3.4495
Max Act: 3.1039. Min Act: -0.1700
Data Index: 4230983 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4495. Min Range: -3.4495
Max Act: 3.0408. Min Act: -0.1700
Data Index: 4509852 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4495. Min Range: -3.4495
Max Act: 3.0566. Min Act: -0.1700
Data Index: 4381623 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4495. Min Range: -3.4495
Max Act: 3.0250. Min Act: -0.1700
Data Index: 7131113 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4495. Min Range: -3.4495
Max Act: 3.0408. Min Act: -0.1700
Data Index: 3715178 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4495. Min Range: -3.4495
Max Act: 3.0408. Min Act: -0.1700
Data Index: 660983 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4495. Min Range: -3.4495
Max Act: 3.0092. Min Act: -0.1700
Data Index: 1109722 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4495. Min Range: -3.4495
Max Act: 3.0092. Min Act: -0.1700
Data Index: 1076944 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4495. Min Range: -3.4495
Max Act: 2.9934. Min Act: -0.1700
Data Index: 3209721 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4495. Min Range: -3.4495
Max Act: 3.0092. Min Act: -0.1700
Data Index: 5049485 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4495. Min Range: -3.4495
Max Act: 2.9934. Min Act: -0.1700
Data Index: 1593417 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4495. Min Range: -3.4495
Max Act: 2.9934. Min Act: -0.1700
Data Index: 6961086 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19