Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1160 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1385. Min Range: -4.1385
Max Act: 4.1385. Min Act: -0.1700
Data Index: 5420808 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1385. Min Range: -4.1385
Max Act: 3.9822. Min Act: -0.1700
Data Index: 6392968 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1385. Min Range: -4.1385
Max Act: 3.9509. Min Act: -0.1700
Data Index: 4785941 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1385. Min Range: -4.1385
Max Act: 3.9197. Min Act: -0.1700
Data Index: 4459490 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1385. Min Range: -4.1385
Max Act: 3.9509. Min Act: -0.1700
Data Index: 1728640 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1385. Min Range: -4.1385
Max Act: 3.9197. Min Act: -0.1700
Data Index: 8407655 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1385. Min Range: -4.1385
Max Act: 3.9197. Min Act: -0.1700
Data Index: 7590052 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1385. Min Range: -4.1385
Max Act: 3.8884. Min Act: -0.1700
Data Index: 1034370 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1385. Min Range: -4.1385
Max Act: 3.8884. Min Act: -0.1700
Data Index: 7341940 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1385. Min Range: -4.1385
Max Act: 3.8884. Min Act: -0.1700
Data Index: 5557447 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1385. Min Range: -4.1385
Max Act: 3.8884. Min Act: -0.1700
Data Index: 3385719 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1385. Min Range: -4.1385
Max Act: 3.8259. Min Act: -0.1700
Data Index: 4683176 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1385. Min Range: -4.1385
Max Act: 3.8259. Min Act: -0.1700
Data Index: 4264000 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1385. Min Range: -4.1385
Max Act: 3.7946. Min Act: -0.1700
Data Index: 1381361 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1385. Min Range: -4.1385
Max Act: 3.7946. Min Act: -0.1700
Data Index: 6734131 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1385. Min Range: -4.1385
Max Act: 3.7946. Min Act: -0.1700
Data Index: 3896241 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1385. Min Range: -4.1385
Max Act: 3.8259. Min Act: -0.1700
Data Index: 4079281 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1385. Min Range: -4.1385
Max Act: 3.7946. Min Act: -0.1700
Data Index: 4156572 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1385. Min Range: -4.1385
Max Act: 3.7946. Min Act: -0.1700
Data Index: 260440 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1385. Min Range: -4.1385
Max Act: 3.7946. Min Act: -0.1700
Data Index: 6635105 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19