Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2790 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6651. Min Range: -5.6651
Max Act: 5.6651. Min Act: -0.1700
Data Index: 5158113 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6651. Min Range: -5.6651
Max Act: 5.6026. Min Act: -0.1700
Data Index: 1998156 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6651. Min Range: -5.6651
Max Act: 5.5713. Min Act: -0.1700
Data Index: 5906856 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6651. Min Range: -5.6651
Max Act: 5.5713. Min Act: -0.1700
Data Index: 5443594 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6651. Min Range: -5.6651
Max Act: 5.4776. Min Act: -0.1700
Data Index: 6757710 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6651. Min Range: -5.6651
Max Act: 5.4151. Min Act: -0.1700
Data Index: 4951645 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6651. Min Range: -5.6651
Max Act: 5.4463. Min Act: -0.1700
Data Index: 6612115 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6651. Min Range: -5.6651
Max Act: 5.4776. Min Act: -0.1700
Data Index: 5906847 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6651. Min Range: -5.6651
Max Act: 5.3838. Min Act: -0.1700
Data Index: 6757699 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6651. Min Range: -5.6651
Max Act: 5.3838. Min Act: -0.1700
Data Index: 1527115 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6651. Min Range: -5.6651
Max Act: 5.3526. Min Act: -0.1700
Data Index: 5056208 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6651. Min Range: -5.6651
Max Act: 5.3526. Min Act: -0.1700
Data Index: 1998139 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6651. Min Range: -5.6651
Max Act: 5.3526. Min Act: -0.1700
Data Index: 5443582 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6651. Min Range: -5.6651
Max Act: 5.4151. Min Act: -0.1700
Data Index: 373449 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6651. Min Range: -5.6651
Max Act: 5.3526. Min Act: -0.1700
Data Index: 5056224 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6651. Min Range: -5.6651
Max Act: 5.3213. Min Act: -0.1700
Data Index: 1495205 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6651. Min Range: -5.6651
Max Act: 5.3526. Min Act: -0.1700
Data Index: 900934 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6651. Min Range: -5.6651
Max Act: 5.3526. Min Act: -0.1700
Data Index: 7122748 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6651. Min Range: -5.6651
Max Act: 5.3213. Min Act: -0.1700
Data Index: 7122763 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6651. Min Range: -5.6651
Max Act: 5.3526. Min Act: -0.1700
Data Index: 6612110 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19