Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3530 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.8838. Min Act: -0.1700
Data Index: 1607035 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.8213. Min Act: -0.1700
Data Index: 2207024 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.6963. Min Act: -0.1700
Data Index: 3012440 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.6651. Min Act: -0.1700
Data Index: 7703326 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.5088. Min Act: -0.1700
Data Index: 6692865 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.3838. Min Act: -0.1700
Data Index: 265201 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.2276. Min Act: -0.1700
Data Index: 1796783 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.2276. Min Act: -0.1700
Data Index: 4743850 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.1651. Min Act: -0.1700
Data Index: 4131133 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.1651. Min Act: -0.1700
Data Index: 3994033 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.1338. Min Act: -0.1700
Data Index: 2635860 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.1338. Min Act: -0.1700
Data Index: 4712459 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.1338. Min Act: -0.1700
Data Index: 6451218 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.1026. Min Act: -0.1700
Data Index: 4483849 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.1026. Min Act: -0.1700
Data Index: 4738447 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.0713. Min Act: -0.1700
Data Index: 5975303 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.0401. Min Act: -0.1700
Data Index: 605870 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.0401. Min Act: -0.1700
Data Index: 3964212 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.0401. Min Act: -0.1700
Data Index: 5797543 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8838. Min Range: -6.8838
Max Act: 5.9776. Min Act: -0.1700
Data Index: 4382330 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19