Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3973 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.3565. Min Act: -0.1700
Data Index: 8511876 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.3253. Min Act: -0.1700
Data Index: 4126611 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.2628. Min Act: -0.1700
Data Index: 105330 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.2315. Min Act: -0.1700
Data Index: 7011792 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.2315. Min Act: -0.1700
Data Index: 2861005 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.1065. Min Act: -0.1700
Data Index: 7971600 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.0753. Min Act: -0.1700
Data Index: 5016635 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.1065. Min Act: -0.1700
Data Index: 3682397 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.0753. Min Act: -0.1700
Data Index: 8774820 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.0753. Min Act: -0.1700
Data Index: 8435157 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.0753. Min Act: -0.1700
Data Index: 2293778 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.0753. Min Act: -0.1700
Data Index: 485106 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.0128. Min Act: -0.1700
Data Index: 3650852 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.9815. Min Act: -0.1700
Data Index: 8123193 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.9815. Min Act: -0.1700
Data Index: 3055377 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.9815. Min Act: -0.1700
Data Index: 6930937 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.9503. Min Act: -0.1700
Data Index: 2806584 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.9503. Min Act: -0.1700
Data Index: 1352995 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.9815. Min Act: -0.1700
Data Index: 8106963 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.9503. Min Act: -0.1700
Data Index: 2439597 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19