Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1514 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1963. Min Range: -7.1963
Max Act: 7.1963. Min Act: -0.1700
Data Index: 5258606 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1963. Min Range: -7.1963
Max Act: 7.0401. Min Act: -0.1700
Data Index: 4269282 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1963. Min Range: -7.1963
Max Act: 7.0088. Min Act: -0.1700
Data Index: 8324420 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1963. Min Range: -7.1963
Max Act: 6.9776. Min Act: -0.1700
Data Index: 3762382 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1963. Min Range: -7.1963
Max Act: 6.8838. Min Act: -0.1700
Data Index: 7091577 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1963. Min Range: -7.1963
Max Act: 6.8526. Min Act: -0.1700
Data Index: 5337438 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1963. Min Range: -7.1963
Max Act: 6.8526. Min Act: -0.1700
Data Index: 2408 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1963. Min Range: -7.1963
Max Act: 6.7901. Min Act: -0.1700
Data Index: 2155587 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1963. Min Range: -7.1963
Max Act: 6.7901. Min Act: -0.1700
Data Index: 6733141 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1963. Min Range: -7.1963
Max Act: 6.7276. Min Act: -0.1700
Data Index: 7417037 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1963. Min Range: -7.1963
Max Act: 6.7276. Min Act: -0.1700
Data Index: 68011 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1963. Min Range: -7.1963
Max Act: 6.6651. Min Act: -0.1700
Data Index: 4722397 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1963. Min Range: -7.1963
Max Act: 6.6338. Min Act: -0.1700
Data Index: 5032398 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1963. Min Range: -7.1963
Max Act: 6.6651. Min Act: -0.1700
Data Index: 2449532 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1963. Min Range: -7.1963
Max Act: 6.6338. Min Act: -0.1700
Data Index: 114337 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1963. Min Range: -7.1963
Max Act: 6.6338. Min Act: -0.1700
Data Index: 1152981 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1963. Min Range: -7.1963
Max Act: 6.6338. Min Act: -0.1700
Data Index: 346997 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1963. Min Range: -7.1963
Max Act: 6.6026. Min Act: -0.1700
Data Index: 3406283 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1963. Min Range: -7.1963
Max Act: 6.5088. Min Act: -0.1700
Data Index: 6824521 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1963. Min Range: -7.1963
Max Act: 6.4776. Min Act: -0.1700
Data Index: 2305643 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19