Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3202 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7209. Min Range: -6.7209
Max Act: 6.7209. Min Act: -0.1700
Data Index: 4409688 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7209. Min Range: -6.7209
Max Act: 6.5647. Min Act: -0.1700
Data Index: 5755114 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7209. Min Range: -6.7209
Max Act: 6.5647. Min Act: -0.1700
Data Index: 3009609 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7209. Min Range: -6.7209
Max Act: 6.4709. Min Act: -0.1700
Data Index: 7707527 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7209. Min Range: -6.7209
Max Act: 6.4084. Min Act: -0.1700
Data Index: 6197138 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7209. Min Range: -6.7209
Max Act: 6.3459. Min Act: -0.1700
Data Index: 2693496 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7209. Min Range: -6.7209
Max Act: 6.3147. Min Act: -0.1700
Data Index: 6096257 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7209. Min Range: -6.7209
Max Act: 6.3147. Min Act: -0.1700
Data Index: 8484737 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7209. Min Range: -6.7209
Max Act: 6.3459. Min Act: -0.1700
Data Index: 8097660 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7209. Min Range: -6.7209
Max Act: 6.2522. Min Act: -0.1700
Data Index: 7387140 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7209. Min Range: -6.7209
Max Act: 6.2834. Min Act: -0.1700
Data Index: 8823965 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7209. Min Range: -6.7209
Max Act: 6.2834. Min Act: -0.1700
Data Index: 4511545 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7209. Min Range: -6.7209
Max Act: 6.2522. Min Act: -0.1700
Data Index: 6721403 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7209. Min Range: -6.7209
Max Act: 6.2834. Min Act: -0.1700
Data Index: 2641024 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7209. Min Range: -6.7209
Max Act: 6.2522. Min Act: -0.1700
Data Index: 1055889 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7209. Min Range: -6.7209
Max Act: 6.2209. Min Act: -0.1700
Data Index: 6400978 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7209. Min Range: -6.7209
Max Act: 6.2209. Min Act: -0.1700
Data Index: 6114605 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7209. Min Range: -6.7209
Max Act: 6.2209. Min Act: -0.1700
Data Index: 77086 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7209. Min Range: -6.7209
Max Act: 6.1897. Min Act: -0.1700
Data Index: 2439327 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7209. Min Range: -6.7209
Max Act: 6.1584. Min Act: -0.1700
Data Index: 5785339 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19