Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5705 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.7143. Min Act: -0.1700
Data Index: 5033673 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.6831. Min Act: -0.1700
Data Index: 4862573 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.2768. Min Act: -0.1700
Data Index: 8679150 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.3081. Min Act: -0.1700
Data Index: 5048654 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.2456. Min Act: -0.1700
Data Index: 4142439 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.2456. Min Act: -0.1700
Data Index: 1457312 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.2143. Min Act: -0.1700
Data Index: 7814399 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.1831. Min Act: -0.1700
Data Index: 314201 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.1831. Min Act: -0.1700
Data Index: 6845213 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.1518. Min Act: -0.1700
Data Index: 7749825 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.0893. Min Act: -0.1700
Data Index: 8144445 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.0893. Min Act: -0.1700
Data Index: 384238 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.0893. Min Act: -0.1700
Data Index: 4641231 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.0581. Min Act: -0.1700
Data Index: 4752631 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.0268. Min Act: -0.1700
Data Index: 2227559 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7143. Min Range: -6.7143
Max Act: 5.9643. Min Act: -0.1700
Data Index: 6915324 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.0268. Min Act: -0.1700
Data Index: 8186433 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7143. Min Range: -6.7143
Max Act: 5.9956. Min Act: -0.1700
Data Index: 1346875 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7143. Min Range: -6.7143
Max Act: 5.9956. Min Act: -0.1700
Data Index: 1934658 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7143. Min Range: -6.7143
Max Act: 5.9331. Min Act: -0.1700
Data Index: 7604215 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19