Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3195 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4262. Min Range: -4.4262
Max Act: 4.4262. Min Act: -0.1700
Data Index: 3277949 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4262. Min Range: -4.4262
Max Act: 4.1762. Min Act: -0.1700
Data Index: 3929601 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4262. Min Range: -4.4262
Max Act: 4.1137. Min Act: -0.1700
Data Index: 5410938 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4262. Min Range: -4.4262
Max Act: 4.0824. Min Act: -0.1700
Data Index: 872989 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4262. Min Range: -4.4262
Max Act: 3.9886. Min Act: -0.1700
Data Index: 2050003 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4262. Min Range: -4.4262
Max Act: 3.9886. Min Act: -0.1700
Data Index: 4476101 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4262. Min Range: -4.4262
Max Act: 3.9886. Min Act: -0.1700
Data Index: 3817682 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4262. Min Range: -4.4262
Max Act: 3.9261. Min Act: -0.1700
Data Index: 7208251 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4262. Min Range: -4.4262
Max Act: 3.8636. Min Act: -0.1700
Data Index: 7979982 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4262. Min Range: -4.4262
Max Act: 3.8948. Min Act: -0.1700
Data Index: 3247876 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4262. Min Range: -4.4262
Max Act: 3.8636. Min Act: -0.1700
Data Index: 736576 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4262. Min Range: -4.4262
Max Act: 3.8636. Min Act: -0.1700
Data Index: 6816486 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4262. Min Range: -4.4262
Max Act: 3.8636. Min Act: -0.1700
Data Index: 1497117 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4262. Min Range: -4.4262
Max Act: 3.8948. Min Act: -0.1700
Data Index: 8099382 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4262. Min Range: -4.4262
Max Act: 3.8479. Min Act: -0.1700
Data Index: 6844336 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4262. Min Range: -4.4262
Max Act: 3.8636. Min Act: -0.1700
Data Index: 4418103 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4262. Min Range: -4.4262
Max Act: 3.8479. Min Act: -0.1700
Data Index: 4372875 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4262. Min Range: -4.4262
Max Act: 3.8010. Min Act: -0.1700
Data Index: 199441 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4262. Min Range: -4.4262
Max Act: 3.7854. Min Act: -0.1700
Data Index: 4023333 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4262. Min Range: -4.4262
Max Act: 3.8010. Min Act: -0.1700
Data Index: 4305392 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19