Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2525 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4338. Min Range: -6.4338
Max Act: 6.4338. Min Act: -0.1700
Data Index: 4567394 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4338. Min Range: -6.4338
Max Act: 6.1838. Min Act: -0.1700
Data Index: 3859901 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4338. Min Range: -6.4338
Max Act: 6.0900. Min Act: -0.1700
Data Index: 1432253 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4338. Min Range: -6.4338
Max Act: 6.0588. Min Act: -0.1700
Data Index: 3765858 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4338. Min Range: -6.4338
Max Act: 5.9963. Min Act: -0.1700
Data Index: 331154 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4338. Min Range: -6.4338
Max Act: 5.9963. Min Act: -0.1700
Data Index: 5411277 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4338. Min Range: -6.4338
Max Act: 5.9650. Min Act: -0.1700
Data Index: 7438452 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4338. Min Range: -6.4338
Max Act: 5.9338. Min Act: -0.1700
Data Index: 7470615 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4338. Min Range: -6.4338
Max Act: 5.9338. Min Act: -0.1700
Data Index: 220641 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4338. Min Range: -6.4338
Max Act: 5.9025. Min Act: -0.1700
Data Index: 4824237 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4338. Min Range: -6.4338
Max Act: 5.8713. Min Act: -0.1700
Data Index: 2434234 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4338. Min Range: -6.4338
Max Act: 5.9338. Min Act: -0.1700
Data Index: 1030221 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4338. Min Range: -6.4338
Max Act: 5.8400. Min Act: -0.1700
Data Index: 5017159 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4338. Min Range: -6.4338
Max Act: 5.8713. Min Act: -0.1700
Data Index: 72314 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4338. Min Range: -6.4338
Max Act: 5.8400. Min Act: -0.1700
Data Index: 6258475 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4338. Min Range: -6.4338
Max Act: 5.8088. Min Act: -0.1700
Data Index: 4496622 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4338. Min Range: -6.4338
Max Act: 5.8088. Min Act: -0.1700
Data Index: 8071397 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4338. Min Range: -6.4338
Max Act: 5.8400. Min Act: -0.1700
Data Index: 8720285 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4338. Min Range: -6.4338
Max Act: 5.8400. Min Act: -0.1700
Data Index: 6005908 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4338. Min Range: -6.4338
Max Act: 5.8400. Min Act: -0.1700
Data Index: 7700627 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19