Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1749 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5622. Min Range: -3.5622
Max Act: 3.5622. Min Act: -0.1700
Data Index: 1994550 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5622. Min Range: -3.5622
Max Act: 3.3742. Min Act: -0.1700
Data Index: 7455765 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5622. Min Range: -3.5622
Max Act: 3.3742. Min Act: -0.1700
Data Index: 4377147 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5622. Min Range: -3.5622
Max Act: 3.3428. Min Act: -0.1700
Data Index: 374259 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5622. Min Range: -3.5622
Max Act: 3.2800. Min Act: -0.1700
Data Index: 1804778 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5622. Min Range: -3.5622
Max Act: 3.2800. Min Act: -0.1700
Data Index: 3423138 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5622. Min Range: -3.5622
Max Act: 3.2800. Min Act: -0.1700
Data Index: 458672 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5622. Min Range: -3.5622
Max Act: 3.2486. Min Act: -0.1700
Data Index: 5428421 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5622. Min Range: -3.5622
Max Act: 3.2486. Min Act: -0.1700
Data Index: 6572205 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5622. Min Range: -3.5622
Max Act: 3.2172. Min Act: -0.1700
Data Index: 6933488 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5622. Min Range: -3.5622
Max Act: 3.1857. Min Act: -0.1700
Data Index: 2995677 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5622. Min Range: -3.5622
Max Act: 3.2172. Min Act: -0.1700
Data Index: 416058 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5622. Min Range: -3.5622
Max Act: 3.2172. Min Act: -0.1700
Data Index: 5846722 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5622. Min Range: -3.5622
Max Act: 3.2172. Min Act: -0.1700
Data Index: 7121562 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5622. Min Range: -3.5622
Max Act: 3.2172. Min Act: -0.1700
Data Index: 2852493 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5622. Min Range: -3.5622
Max Act: 3.1857. Min Act: -0.1700
Data Index: 6764336 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5622. Min Range: -3.5622
Max Act: 3.1857. Min Act: -0.1700
Data Index: 275614 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5622. Min Range: -3.5622
Max Act: 3.1857. Min Act: -0.1700
Data Index: 5304564 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5622. Min Range: -3.5622
Max Act: 3.1857. Min Act: -0.1700
Data Index: 170859 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5622. Min Range: -3.5622
Max Act: 3.2172. Min Act: -0.1700
Data Index: 7233485 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19