Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4749 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4444. Min Range: -9.4444
Max Act: 9.4444. Min Act: -0.1700
Data Index: 526026 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4444. Min Range: -9.4444
Max Act: 9.4444. Min Act: -0.1700
Data Index: 923310 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4444. Min Range: -9.4444
Max Act: 9.3819. Min Act: -0.1700
Data Index: 5827316 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4444. Min Range: -9.4444
Max Act: 9.1944. Min Act: -0.1700
Data Index: 4081994 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4444. Min Range: -9.4444
Max Act: 9.1319. Min Act: -0.1700
Data Index: 4109516 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4444. Min Range: -9.4444
Max Act: 9.1319. Min Act: -0.1700
Data Index: 244533 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4444. Min Range: -9.4444
Max Act: 9.1319. Min Act: -0.1700
Data Index: 6903124 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4444. Min Range: -9.4444
Max Act: 9.0069. Min Act: -0.1700
Data Index: 1333125 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4444. Min Range: -9.4444
Max Act: 8.8819. Min Act: -0.1700
Data Index: 6330590 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4444. Min Range: -9.4444
Max Act: 8.8819. Min Act: -0.1700
Data Index: 5701185 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4444. Min Range: -9.4444
Max Act: 8.8194. Min Act: -0.1700
Data Index: 4904847 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4444. Min Range: -9.4444
Max Act: 8.8819. Min Act: -0.1700
Data Index: 20218 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4444. Min Range: -9.4444
Max Act: 8.8194. Min Act: -0.1700
Data Index: 2056119 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4444. Min Range: -9.4444
Max Act: 8.8194. Min Act: -0.1700
Data Index: 2848575 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4444. Min Range: -9.4444
Max Act: 8.7569. Min Act: -0.1700
Data Index: 6111225 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4444. Min Range: -9.4444
Max Act: 8.6944. Min Act: -0.1700
Data Index: 2101500 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4444. Min Range: -9.4444
Max Act: 8.7569. Min Act: -0.1700
Data Index: 6739382 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4444. Min Range: -9.4444
Max Act: 8.7569. Min Act: -0.1700
Data Index: 2129780 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4444. Min Range: -9.4444
Max Act: 8.7569. Min Act: -0.1700
Data Index: 2469153 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4444. Min Range: -9.4444
Max Act: 8.7569. Min Act: -0.1700
Data Index: 244534 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19