Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5390 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.6971. Min Act: -0.1700
Data Index: 4347571 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.6811. Min Act: -0.1700
Data Index: 1690995 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.6811. Min Act: -0.1700
Data Index: 8549225 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.6651. Min Act: -0.1700
Data Index: 4347572 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.6330. Min Act: -0.1700
Data Index: 3082745 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.6330. Min Act: -0.1700
Data Index: 5284117 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.6330. Min Act: -0.1700
Data Index: 2313107 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.6330. Min Act: -0.1700
Data Index: 7317786 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5847. Min Act: -0.1700
Data Index: 4169988 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5847. Min Act: -0.1700
Data Index: 3062157 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5847. Min Act: -0.1700
Data Index: 5190696 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5686. Min Act: -0.1700
Data Index: 1690996 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5686. Min Act: -0.1700
Data Index: 1113114 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5686. Min Act: -0.1700
Data Index: 8529941 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5686. Min Act: -0.1700
Data Index: 5069916 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5525. Min Act: -0.1700
Data Index: 4337935 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5525. Min Act: -0.1700
Data Index: 4445162 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5525. Min Act: -0.1700
Data Index: 5784919 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5363. Min Act: -0.1700
Data Index: 1123004 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5525. Min Act: -0.1700
Data Index: 3064649 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19