Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 602 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9754. Min Range: -5.9754
Max Act: 5.9754. Min Act: -0.1700
Data Index: 3662995 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9754. Min Range: -5.9754
Max Act: 5.6004. Min Act: -0.1700
Data Index: 1763689 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9754. Min Range: -5.9754
Max Act: 5.3504. Min Act: -0.1700
Data Index: 689636 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9754. Min Range: -5.9754
Max Act: 5.2567. Min Act: -0.1700
Data Index: 3984807 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9754. Min Range: -5.9754
Max Act: 5.2254. Min Act: -0.1700
Data Index: 7257346 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9754. Min Range: -5.9754
Max Act: 5.1629. Min Act: -0.1700
Data Index: 1564410 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9754. Min Range: -5.9754
Max Act: 5.1629. Min Act: -0.1700
Data Index: 2273266 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9754. Min Range: -5.9754
Max Act: 5.1629. Min Act: -0.1700
Data Index: 7222541 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9754. Min Range: -5.9754
Max Act: 5.1004. Min Act: -0.1700
Data Index: 4601648 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9754. Min Range: -5.9754
Max Act: 5.1004. Min Act: -0.1700
Data Index: 4132667 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9754. Min Range: -5.9754
Max Act: 5.0379. Min Act: -0.1700
Data Index: 1052184 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9754. Min Range: -5.9754
Max Act: 5.0692. Min Act: -0.1700
Data Index: 116886 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9754. Min Range: -5.9754
Max Act: 5.0379. Min Act: -0.1700
Data Index: 2843049 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9754. Min Range: -5.9754
Max Act: 5.0067. Min Act: -0.1700
Data Index: 6337996 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9754. Min Range: -5.9754
Max Act: 5.0067. Min Act: -0.1700
Data Index: 8213058 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9754. Min Range: -5.9754
Max Act: 4.9442. Min Act: -0.1700
Data Index: 959726 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9754. Min Range: -5.9754
Max Act: 4.9442. Min Act: -0.1700
Data Index: 2003032 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9754. Min Range: -5.9754
Max Act: 4.9442. Min Act: -0.1700
Data Index: 7386940 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9754. Min Range: -5.9754
Max Act: 4.9442. Min Act: -0.1700
Data Index: 3167939 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9754. Min Range: -5.9754
Max Act: 4.9442. Min Act: -0.1700
Data Index: 2889367 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19