Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3644 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3700. Min Range: -4.3700
Max Act: 4.3700. Min Act: -0.1700
Data Index: 5406323 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3700. Min Range: -4.3700
Max Act: 3.9637. Min Act: -0.1700
Data Index: 929879 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3700. Min Range: -4.3700
Max Act: 3.6353. Min Act: -0.1700
Data Index: 5088346 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3700. Min Range: -4.3700
Max Act: 3.5883. Min Act: -0.1700
Data Index: 3796087 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3700. Min Range: -4.3700
Max Act: 3.5413. Min Act: -0.1700
Data Index: 1067081 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3700. Min Range: -4.3700
Max Act: 3.4944. Min Act: -0.1700
Data Index: 7842376 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3700. Min Range: -4.3700
Max Act: 3.4474. Min Act: -0.1700
Data Index: 5183927 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3700. Min Range: -4.3700
Max Act: 3.4630. Min Act: -0.1700
Data Index: 3971664 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3700. Min Range: -4.3700
Max Act: 3.4317. Min Act: -0.1700
Data Index: 8716945 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3700. Min Range: -4.3700
Max Act: 3.3847. Min Act: -0.1700
Data Index: 5395135 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3700. Min Range: -4.3700
Max Act: 3.4003. Min Act: -0.1700
Data Index: 3681499 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3700. Min Range: -4.3700
Max Act: 3.4003. Min Act: -0.1700
Data Index: 8342369 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3700. Min Range: -4.3700
Max Act: 3.3690. Min Act: -0.1700
Data Index: 1277118 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3700. Min Range: -4.3700
Max Act: 3.4317. Min Act: -0.1700
Data Index: 2119574 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3700. Min Range: -4.3700
Max Act: 3.3533. Min Act: -0.1700
Data Index: 3480077 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3700. Min Range: -4.3700
Max Act: 3.4003. Min Act: -0.1700
Data Index: 7118476 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3700. Min Range: -4.3700
Max Act: 3.3847. Min Act: -0.1700
Data Index: 4827227 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3700. Min Range: -4.3700
Max Act: 3.3690. Min Act: -0.1700
Data Index: 4936384 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3700. Min Range: -4.3700
Max Act: 3.3533. Min Act: -0.1700
Data Index: 8171489 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3700. Min Range: -4.3700
Max Act: 3.2748. Min Act: -0.1700
Data Index: 4766880 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19