Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3614 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5747. Min Range: -4.5747
Max Act: 4.5747. Min Act: -0.1700
Data Index: 4585564 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5747. Min Range: -4.5747
Max Act: 4.5747. Min Act: -0.1700
Data Index: 4585563 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5747. Min Range: -4.5747
Max Act: 4.4497. Min Act: -0.1700
Data Index: 1191755 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5747. Min Range: -4.5747
Max Act: 4.2622. Min Act: -0.1700
Data Index: 3825419 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5747. Min Range: -4.5747
Max Act: 4.2309. Min Act: -0.1700
Data Index: 8251190 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5747. Min Range: -4.5747
Max Act: 4.2622. Min Act: -0.1700
Data Index: 4760016 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5747. Min Range: -4.5747
Max Act: 4.2309. Min Act: -0.1700
Data Index: 2840446 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5747. Min Range: -4.5747
Max Act: 4.1684. Min Act: -0.1700
Data Index: 135439 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5747. Min Range: -4.5747
Max Act: 4.1997. Min Act: -0.1700
Data Index: 5314163 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5747. Min Range: -4.5747
Max Act: 4.1371. Min Act: -0.1700
Data Index: 3598995 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5747. Min Range: -4.5747
Max Act: 4.1684. Min Act: -0.1700
Data Index: 8798783 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5747. Min Range: -4.5747
Max Act: 4.1371. Min Act: -0.1700
Data Index: 8490734 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5747. Min Range: -4.5747
Max Act: 4.1684. Min Act: -0.1700
Data Index: 6423212 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5747. Min Range: -4.5747
Max Act: 4.1684. Min Act: -0.1700
Data Index: 6191696 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5747. Min Range: -4.5747
Max Act: 4.1684. Min Act: -0.1700
Data Index: 4115756 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5747. Min Range: -4.5747
Max Act: 4.1371. Min Act: -0.1699
Data Index: 1349303 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5747. Min Range: -4.5747
Max Act: 4.1059. Min Act: -0.1699
Data Index: 7834297 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5747. Min Range: -4.5747
Max Act: 4.1371. Min Act: -0.1700
Data Index: 2783988 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5747. Min Range: -4.5747
Max Act: 4.1059. Min Act: -0.1700
Data Index: 2695515 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5747. Min Range: -4.5747
Max Act: 4.1059. Min Act: -0.1700
Data Index: 1384977 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19