Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2668 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5667. Min Range: -6.5667
Max Act: 6.5667. Min Act: -0.1700
Data Index: 1748962 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5667. Min Range: -6.5667
Max Act: 6.4417. Min Act: -0.1700
Data Index: 3083189 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5667. Min Range: -6.5667
Max Act: 6.3792. Min Act: -0.1700
Data Index: 5969690 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5667. Min Range: -6.5667
Max Act: 6.2229. Min Act: -0.1700
Data Index: 5895451 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5667. Min Range: -6.5667
Max Act: 6.2229. Min Act: -0.1700
Data Index: 5112169 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5667. Min Range: -6.5667
Max Act: 6.1292. Min Act: -0.1700
Data Index: 6050489 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5667. Min Range: -6.5667
Max Act: 6.0354. Min Act: -0.1700
Data Index: 1644702 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5667. Min Range: -6.5667
Max Act: 6.0042. Min Act: -0.1700
Data Index: 37218 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5667. Min Range: -6.5667
Max Act: 6.0042. Min Act: -0.1700
Data Index: 6264960 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5667. Min Range: -6.5667
Max Act: 6.0354. Min Act: -0.1700
Data Index: 8224852 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5667. Min Range: -6.5667
Max Act: 5.9729. Min Act: -0.1700
Data Index: 2761327 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5667. Min Range: -6.5667
Max Act: 5.9729. Min Act: -0.1700
Data Index: 8314636 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5667. Min Range: -6.5667
Max Act: 5.9729. Min Act: -0.1700
Data Index: 7276624 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5667. Min Range: -6.5667
Max Act: 5.9729. Min Act: -0.1700
Data Index: 948310 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5667. Min Range: -6.5667
Max Act: 5.9104. Min Act: -0.1700
Data Index: 214022 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5667. Min Range: -6.5667
Max Act: 5.9104. Min Act: -0.1700
Data Index: 6969034 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5667. Min Range: -6.5667
Max Act: 5.8792. Min Act: -0.1700
Data Index: 8276834 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5667. Min Range: -6.5667
Max Act: 5.8792. Min Act: -0.1700
Data Index: 5830824 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5667. Min Range: -6.5667
Max Act: 5.8792. Min Act: -0.1700
Data Index: 1174187 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5667. Min Range: -6.5667
Max Act: 5.8479. Min Act: -0.1700
Data Index: 4577700 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19