Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1021 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3072. Min Range: -5.3072
Max Act: 5.3072. Min Act: -0.1700
Data Index: 3340911 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3072. Min Range: -5.3072
Max Act: 4.9009. Min Act: -0.1700
Data Index: 201578 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3072. Min Range: -5.3072
Max Act: 4.7134. Min Act: -0.1700
Data Index: 7579641 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3072. Min Range: -5.3072
Max Act: 4.6509. Min Act: -0.1700
Data Index: 8522497 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3072. Min Range: -5.3072
Max Act: 4.6509. Min Act: -0.1700
Data Index: 3563270 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3072. Min Range: -5.3072
Max Act: 4.6509. Min Act: -0.1700
Data Index: 1261692 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3072. Min Range: -5.3072
Max Act: 4.6197. Min Act: -0.1700
Data Index: 3911770 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3072. Min Range: -5.3072
Max Act: 4.6197. Min Act: -0.1700
Data Index: 666429 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3072. Min Range: -5.3072
Max Act: 4.5259. Min Act: -0.1700
Data Index: 909485 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3072. Min Range: -5.3072
Max Act: 4.5259. Min Act: -0.1700
Data Index: 4344265 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3072. Min Range: -5.3072
Max Act: 4.5259. Min Act: -0.1700
Data Index: 6204603 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3072. Min Range: -5.3072
Max Act: 4.5259. Min Act: -0.1700
Data Index: 7255905 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3072. Min Range: -5.3072
Max Act: 4.4634. Min Act: -0.1700
Data Index: 5131955 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3072. Min Range: -5.3072
Max Act: 4.4634. Min Act: -0.1700
Data Index: 4707275 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3072. Min Range: -5.3072
Max Act: 4.4634. Min Act: -0.1700
Data Index: 6678612 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3072. Min Range: -5.3072
Max Act: 4.4322. Min Act: -0.1700
Data Index: 5845368 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3072. Min Range: -5.3072
Max Act: 4.4322. Min Act: -0.1700
Data Index: 2767755 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3072. Min Range: -5.3072
Max Act: 4.4009. Min Act: -0.1700
Data Index: 6799007 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3072. Min Range: -5.3072
Max Act: 4.4322. Min Act: -0.1700
Data Index: 7370199 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3072. Min Range: -5.3072
Max Act: 4.3696. Min Act: -0.1700
Data Index: 2303661 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19