Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2582 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.3646. Min Act: -0.1700
Data Index: 3215261 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.2083. Min Act: -0.1700
Data Index: 2466281 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.0521. Min Act: -0.1700
Data Index: 7069288 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.0208. Min Act: -0.1700
Data Index: 3201070 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.9583. Min Act: -0.1700
Data Index: 5561197 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.9896. Min Act: -0.1700
Data Index: 1780049 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.9583. Min Act: -0.1700
Data Index: 1116457 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.9271. Min Act: -0.1700
Data Index: 2365608 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.8958. Min Act: -0.1700
Data Index: 650199 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.8333. Min Act: -0.1700
Data Index: 3955193 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.8646. Min Act: -0.1700
Data Index: 8373559 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.8333. Min Act: -0.1700
Data Index: 1002831 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.8646. Min Act: -0.1700
Data Index: 1940280 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.8333. Min Act: -0.1700
Data Index: 260363 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.8333. Min Act: -0.1700
Data Index: 2127723 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.8021. Min Act: -0.1700
Data Index: 5898908 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.8333. Min Act: -0.1700
Data Index: 8772877 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.8021. Min Act: -0.1700
Data Index: 7900572 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.7708. Min Act: -0.1700
Data Index: 247599 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.7708. Min Act: -0.1700
Data Index: 3636359 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19