Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 783 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0647. Min Range: -5.0647
Max Act: 5.0647. Min Act: -0.1700
Data Index: 2801659 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0647. Min Range: -5.0647
Max Act: 5.0022. Min Act: -0.1700
Data Index: 4387570 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0647. Min Range: -5.0647
Max Act: 5.0022. Min Act: -0.1700
Data Index: 4309346 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0647. Min Range: -5.0647
Max Act: 4.9397. Min Act: -0.1700
Data Index: 3120762 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0647. Min Range: -5.0647
Max Act: 4.9397. Min Act: -0.1700
Data Index: 5679503 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0647. Min Range: -5.0647
Max Act: 4.9085. Min Act: -0.1700
Data Index: 1501524 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0647. Min Range: -5.0647
Max Act: 4.8460. Min Act: -0.1700
Data Index: 4988352 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0647. Min Range: -5.0647
Max Act: 4.8460. Min Act: -0.1700
Data Index: 3476903 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0647. Min Range: -5.0647
Max Act: 4.8460. Min Act: -0.1700
Data Index: 375884 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0647. Min Range: -5.0647
Max Act: 4.8460. Min Act: -0.1700
Data Index: 2723011 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0647. Min Range: -5.0647
Max Act: 4.7835. Min Act: -0.1700
Data Index: 1974128 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0647. Min Range: -5.0647
Max Act: 4.7835. Min Act: -0.1700
Data Index: 3245754 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0647. Min Range: -5.0647
Max Act: 4.8147. Min Act: -0.1700
Data Index: 2786043 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0647. Min Range: -5.0647
Max Act: 4.7522. Min Act: -0.1700
Data Index: 7277686 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0647. Min Range: -5.0647
Max Act: 4.7522. Min Act: -0.1700
Data Index: 8161834 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0647. Min Range: -5.0647
Max Act: 4.7522. Min Act: -0.1700
Data Index: 2342756 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0647. Min Range: -5.0647
Max Act: 4.7522. Min Act: -0.1700
Data Index: 4998823 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0647. Min Range: -5.0647
Max Act: 4.7210. Min Act: -0.1700
Data Index: 8363942 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0647. Min Range: -5.0647
Max Act: 4.7210. Min Act: -0.1700
Data Index: 8071520 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0647. Min Range: -5.0647
Max Act: 4.6585. Min Act: -0.1700
Data Index: 5509560 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19