Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2026 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9550. Min Range: -5.9550
Max Act: 5.9550. Min Act: -0.1700
Data Index: 2517404 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9550. Min Range: -5.9550
Max Act: 5.9550. Min Act: -0.1700
Data Index: 6706415 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9550. Min Range: -5.9550
Max Act: 5.7363. Min Act: -0.1700
Data Index: 1058476 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9550. Min Range: -5.9550
Max Act: 5.7050. Min Act: -0.1700
Data Index: 6125959 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9550. Min Range: -5.9550
Max Act: 5.6425. Min Act: -0.1700
Data Index: 1977093 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9550. Min Range: -5.9550
Max Act: 5.6738. Min Act: -0.1700
Data Index: 8796764 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9550. Min Range: -5.9550
Max Act: 5.6425. Min Act: -0.1700
Data Index: 8337083 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9550. Min Range: -5.9550
Max Act: 5.6425. Min Act: -0.1700
Data Index: 4375620 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9550. Min Range: -5.9550
Max Act: 5.5800. Min Act: -0.1700
Data Index: 7576667 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9550. Min Range: -5.9550
Max Act: 5.5800. Min Act: -0.1700
Data Index: 5328314 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9550. Min Range: -5.9550
Max Act: 5.5800. Min Act: -0.1700
Data Index: 5425481 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9550. Min Range: -5.9550
Max Act: 5.5488. Min Act: -0.1700
Data Index: 825380 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9550. Min Range: -5.9550
Max Act: 5.5175. Min Act: -0.1700
Data Index: 2079872 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9550. Min Range: -5.9550
Max Act: 5.5175. Min Act: -0.1700
Data Index: 7341211 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9550. Min Range: -5.9550
Max Act: 5.5175. Min Act: -0.1700
Data Index: 4796885 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9550. Min Range: -5.9550
Max Act: 5.5175. Min Act: -0.1700
Data Index: 764570 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9550. Min Range: -5.9550
Max Act: 5.5175. Min Act: -0.1700
Data Index: 6509032 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9550. Min Range: -5.9550
Max Act: 5.4550. Min Act: -0.1700
Data Index: 6402035 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9550. Min Range: -5.9550
Max Act: 5.4863. Min Act: -0.1700
Data Index: 3130688 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9550. Min Range: -5.9550
Max Act: 5.4863. Min Act: -0.1700
Data Index: 423272 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19