Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3909 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9960. Min Range: -9.9960
Max Act: 9.9960. Min Act: -0.1700
Data Index: 383743 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9960. Min Range: -9.9960
Max Act: 9.6835. Min Act: -0.1700
Data Index: 5604562 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9960. Min Range: -9.9960
Max Act: 9.6835. Min Act: -0.1700
Data Index: 83378 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9960. Min Range: -9.9960
Max Act: 9.5585. Min Act: -0.1700
Data Index: 7850008 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9960. Min Range: -9.9960
Max Act: 9.5585. Min Act: -0.1700
Data Index: 648451 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9960. Min Range: -9.9960
Max Act: 9.5585. Min Act: -0.1700
Data Index: 7547465 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9960. Min Range: -9.9960
Max Act: 9.4960. Min Act: -0.1700
Data Index: 3186333 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9960. Min Range: -9.9960
Max Act: 9.4335. Min Act: -0.1700
Data Index: 7870592 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9960. Min Range: -9.9960
Max Act: 9.4960. Min Act: -0.1700
Data Index: 2233708 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9960. Min Range: -9.9960
Max Act: 9.3710. Min Act: -0.1700
Data Index: 3055722 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9960. Min Range: -9.9960
Max Act: 9.3710. Min Act: -0.1700
Data Index: 3494758 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9960. Min Range: -9.9960
Max Act: 9.3085. Min Act: -0.1700
Data Index: 7604142 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9960. Min Range: -9.9960
Max Act: 9.2460. Min Act: -0.1700
Data Index: 2281453 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9960. Min Range: -9.9960
Max Act: 9.2460. Min Act: -0.1700
Data Index: 1293746 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9960. Min Range: -9.9960
Max Act: 9.2460. Min Act: -0.1700
Data Index: 3122953 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9960. Min Range: -9.9960
Max Act: 9.1210. Min Act: -0.1700
Data Index: 3761444 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9960. Min Range: -9.9960
Max Act: 9.1835. Min Act: -0.1700
Data Index: 4081854 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9960. Min Range: -9.9960
Max Act: 9.1835. Min Act: -0.1700
Data Index: 1013047 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9960. Min Range: -9.9960
Max Act: 9.1835. Min Act: -0.1700
Data Index: 6478973 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9960. Min Range: -9.9960
Max Act: 9.1210. Min Act: -0.1700
Data Index: 4211665 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19