Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4152 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1555. Min Range: -4.1555
Max Act: 4.1555. Min Act: -0.1700
Data Index: 5428623 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1555. Min Range: -4.1555
Max Act: 3.7491. Min Act: -0.1700
Data Index: 3323548 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1555. Min Range: -4.1555
Max Act: 3.6396. Min Act: -0.1700
Data Index: 5683285 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1555. Min Range: -4.1555
Max Act: 3.6396. Min Act: -0.1700
Data Index: 1336832 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1555. Min Range: -4.1555
Max Act: 3.6083. Min Act: -0.1700
Data Index: 2955883 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1555. Min Range: -4.1555
Max Act: 3.5926. Min Act: -0.1700
Data Index: 5830636 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1555. Min Range: -4.1555
Max Act: 3.5926. Min Act: -0.1700
Data Index: 4213302 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1555. Min Range: -4.1555
Max Act: 3.5613. Min Act: -0.1700
Data Index: 4639222 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1555. Min Range: -4.1555
Max Act: 3.5457. Min Act: -0.1700
Data Index: 5602482 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1555. Min Range: -4.1555
Max Act: 3.5457. Min Act: -0.1700
Data Index: 4932349 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1555. Min Range: -4.1555
Max Act: 3.5613. Min Act: -0.1700
Data Index: 4473478 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1555. Min Range: -4.1555
Max Act: 3.5457. Min Act: -0.1700
Data Index: 3664316 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1555. Min Range: -4.1555
Max Act: 3.5300. Min Act: -0.1700
Data Index: 1213782 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1555. Min Range: -4.1555
Max Act: 3.5300. Min Act: -0.1700
Data Index: 6483105 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1555. Min Range: -4.1555
Max Act: 3.5144. Min Act: -0.1700
Data Index: 2350142 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1555. Min Range: -4.1555
Max Act: 3.4987. Min Act: -0.1700
Data Index: 568350 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1555. Min Range: -4.1555
Max Act: 3.4987. Min Act: -0.1700
Data Index: 2764433 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1555. Min Range: -4.1555
Max Act: 3.4987. Min Act: -0.1700
Data Index: 6020499 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1555. Min Range: -4.1555
Max Act: 3.4987. Min Act: -0.1700
Data Index: 5802638 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1555. Min Range: -4.1555
Max Act: 3.4830. Min Act: -0.1700
Data Index: 2414248 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19