Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 55 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.6700. Min Act: -0.1700
Data Index: 5755478 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.5763. Min Act: -0.1700
Data Index: 5755477 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.5138. Min Act: -0.1700
Data Index: 4373835 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.5138. Min Act: -0.1700
Data Index: 2075378 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.5138. Min Act: -0.1700
Data Index: 632769 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.4825. Min Act: -0.1700
Data Index: 4575213 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.4513. Min Act: -0.1700
Data Index: 5405328 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.4513. Min Act: -0.1700
Data Index: 139592 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.4200. Min Act: -0.1700
Data Index: 5352161 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.3887. Min Act: -0.1700
Data Index: 3746540 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.3887. Min Act: -0.1700
Data Index: 4716193 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.3887. Min Act: -0.1700
Data Index: 4771272 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.3887. Min Act: -0.1700
Data Index: 3630424 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.3575. Min Act: -0.1700
Data Index: 8778323 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.3887. Min Act: -0.1700
Data Index: 5339437 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.3887. Min Act: -0.1700
Data Index: 3908822 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.3575. Min Act: -0.1700
Data Index: 1571684 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.3575. Min Act: -0.1700
Data Index: 3895343 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.3262. Min Act: -0.1700
Data Index: 7464823 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.3575. Min Act: -0.1700
Data Index: 1708672 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19