Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3900 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2623. Min Range: -6.2623
Max Act: 6.2623. Min Act: -0.1700
Data Index: 8340699 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2623. Min Range: -6.2623
Max Act: 6.2311. Min Act: -0.1700
Data Index: 5292649 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2623. Min Range: -6.2623
Max Act: 6.1998. Min Act: -0.1700
Data Index: 7261466 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2623. Min Range: -6.2623
Max Act: 6.1686. Min Act: -0.1700
Data Index: 3115082 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2623. Min Range: -6.2623
Max Act: 5.9811. Min Act: -0.1700
Data Index: 8456590 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2623. Min Range: -6.2623
Max Act: 5.9811. Min Act: -0.1700
Data Index: 7555290 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2623. Min Range: -6.2623
Max Act: 5.9186. Min Act: -0.1700
Data Index: 8356920 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2623. Min Range: -6.2623
Max Act: 5.9186. Min Act: -0.1700
Data Index: 2421136 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2623. Min Range: -6.2623
Max Act: 5.9186. Min Act: -0.1700
Data Index: 526669 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2623. Min Range: -6.2623
Max Act: 5.8561. Min Act: -0.1700
Data Index: 6522030 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2623. Min Range: -6.2623
Max Act: 5.9186. Min Act: -0.1700
Data Index: 7421664 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2623. Min Range: -6.2623
Max Act: 5.8561. Min Act: -0.1700
Data Index: 2868560 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2623. Min Range: -6.2623
Max Act: 5.8873. Min Act: -0.1700
Data Index: 5984793 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2623. Min Range: -6.2623
Max Act: 5.8248. Min Act: -0.1700
Data Index: 962830 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2623. Min Range: -6.2623
Max Act: 5.8248. Min Act: -0.1700
Data Index: 5419394 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2623. Min Range: -6.2623
Max Act: 5.8248. Min Act: -0.1700
Data Index: 2862824 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2623. Min Range: -6.2623
Max Act: 5.8248. Min Act: -0.1700
Data Index: 4073088 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2623. Min Range: -6.2623
Max Act: 5.7936. Min Act: -0.1700
Data Index: 3241980 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2623. Min Range: -6.2623
Max Act: 5.7623. Min Act: -0.1700
Data Index: 4530633 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2623. Min Range: -6.2623
Max Act: 5.7936. Min Act: -0.1700
Data Index: 158250 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19