Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 43 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9050. Min Range: -5.9050
Max Act: 5.9050. Min Act: -0.1700
Data Index: 2195446 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9050. Min Range: -5.9050
Max Act: 5.7800. Min Act: -0.1700
Data Index: 96914 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9050. Min Range: -5.9050
Max Act: 5.6862. Min Act: -0.1700
Data Index: 8310275 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9050. Min Range: -5.9050
Max Act: 5.6237. Min Act: -0.1700
Data Index: 906342 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9050. Min Range: -5.9050
Max Act: 5.6237. Min Act: -0.1700
Data Index: 5266878 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9050. Min Range: -5.9050
Max Act: 5.5925. Min Act: -0.1700
Data Index: 3112862 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9050. Min Range: -5.9050
Max Act: 5.5925. Min Act: -0.1700
Data Index: 3636477 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9050. Min Range: -5.9050
Max Act: 5.5925. Min Act: -0.1700
Data Index: 1185809 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9050. Min Range: -5.9050
Max Act: 5.5925. Min Act: -0.1700
Data Index: 8311409 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9050. Min Range: -5.9050
Max Act: 5.5925. Min Act: -0.1700
Data Index: 5759394 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9050. Min Range: -5.9050
Max Act: 5.5612. Min Act: -0.1700
Data Index: 6158011 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9050. Min Range: -5.9050
Max Act: 5.5612. Min Act: -0.1700
Data Index: 3309742 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9050. Min Range: -5.9050
Max Act: 5.5300. Min Act: -0.1700
Data Index: 5010225 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9050. Min Range: -5.9050
Max Act: 5.4987. Min Act: -0.1700
Data Index: 3001107 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9050. Min Range: -5.9050
Max Act: 5.5300. Min Act: -0.1700
Data Index: 3134121 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9050. Min Range: -5.9050
Max Act: 5.5300. Min Act: -0.1700
Data Index: 2495913 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9050. Min Range: -5.9050
Max Act: 5.4675. Min Act: -0.1700
Data Index: 5346068 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9050. Min Range: -5.9050
Max Act: 5.4675. Min Act: -0.1700
Data Index: 399080 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9050. Min Range: -5.9050
Max Act: 5.4675. Min Act: -0.1700
Data Index: 968445 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9050. Min Range: -5.9050
Max Act: 5.4675. Min Act: -0.1700
Data Index: 1706180 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19