Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4487 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5802. Min Range: -6.5802
Max Act: 6.5802. Min Act: -0.1700
Data Index: 3542010 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5802. Min Range: -6.5802
Max Act: 6.5490. Min Act: -0.1700
Data Index: 3822726 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5802. Min Range: -6.5802
Max Act: 6.4865. Min Act: -0.1700
Data Index: 2952411 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5802. Min Range: -6.5802
Max Act: 6.4552. Min Act: -0.1700
Data Index: 3447673 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5802. Min Range: -6.5802
Max Act: 6.3615. Min Act: -0.1700
Data Index: 1258507 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5802. Min Range: -6.5802
Max Act: 6.3927. Min Act: -0.1700
Data Index: 8307080 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5802. Min Range: -6.5802
Max Act: 6.3615. Min Act: -0.1700
Data Index: 3988164 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5802. Min Range: -6.5802
Max Act: 6.2990. Min Act: -0.1700
Data Index: 1439140 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5802. Min Range: -6.5802
Max Act: 6.2990. Min Act: -0.1700
Data Index: 338662 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5802. Min Range: -6.5802
Max Act: 6.2052. Min Act: -0.1700
Data Index: 7507766 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5802. Min Range: -6.5802
Max Act: 6.2052. Min Act: -0.1700
Data Index: 2103232 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5802. Min Range: -6.5802
Max Act: 6.1740. Min Act: -0.1700
Data Index: 1409061 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5802. Min Range: -6.5802
Max Act: 6.1740. Min Act: -0.1700
Data Index: 5300780 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5802. Min Range: -6.5802
Max Act: 6.1740. Min Act: -0.1700
Data Index: 3532782 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5802. Min Range: -6.5802
Max Act: 6.1740. Min Act: -0.1700
Data Index: 4624435 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5802. Min Range: -6.5802
Max Act: 6.1740. Min Act: -0.1700
Data Index: 218643 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5802. Min Range: -6.5802
Max Act: 6.1427. Min Act: -0.1700
Data Index: 1002999 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5802. Min Range: -6.5802
Max Act: 6.1115. Min Act: -0.1700
Data Index: 4953804 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5802. Min Range: -6.5802
Max Act: 6.1115. Min Act: -0.1700
Data Index: 133913 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5802. Min Range: -6.5802
Max Act: 6.1115. Min Act: -0.1700
Data Index: 807700 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19