Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1763 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2487. Min Range: -7.2487
Max Act: 7.2487. Min Act: -0.1700
Data Index: 1771790 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2487. Min Range: -7.2487
Max Act: 7.1237. Min Act: -0.1700
Data Index: 7551853 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2487. Min Range: -7.2487
Max Act: 7.0300. Min Act: -0.1700
Data Index: 5617985 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.9675. Min Act: -0.1700
Data Index: 2618448 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.9050. Min Act: -0.1700
Data Index: 409104 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.8425. Min Act: -0.1700
Data Index: 3818731 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.8737. Min Act: -0.1700
Data Index: 5052740 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.8737. Min Act: -0.1700
Data Index: 8743113 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.8112. Min Act: -0.1700
Data Index: 4057732 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.8112. Min Act: -0.1700
Data Index: 652595 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.7800. Min Act: -0.1700
Data Index: 2413809 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.7175. Min Act: -0.1700
Data Index: 4843890 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.7175. Min Act: -0.1700
Data Index: 4078756 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.7175. Min Act: -0.1700
Data Index: 292324 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.7175. Min Act: -0.1700
Data Index: 7326548 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.6550. Min Act: -0.1700
Data Index: 939696 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.6862. Min Act: -0.1700
Data Index: 303259 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.6862. Min Act: -0.1700
Data Index: 7914354 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.6550. Min Act: -0.1700
Data Index: 198722 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.6550. Min Act: -0.1700
Data Index: 1528023 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19