Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2026 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.4049. Min Act: -0.1700
Data Index: 6197425 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.2814. Min Act: -0.1700
Data Index: 1569606 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1933. Min Act: -0.1700
Data Index: 3735262 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1757. Min Act: -0.1700
Data Index: 7067865 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.2109. Min Act: -0.1700
Data Index: 1569608 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1757. Min Act: -0.1700
Data Index: 5163445 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1757. Min Act: -0.1700
Data Index: 1569605 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1757. Min Act: -0.1700
Data Index: 3735261 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1933. Min Act: -0.1693
Data Index: 4624090 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1581. Min Act: -0.1700
Data Index: 1569607 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1581. Min Act: -0.1700
Data Index: 5626131 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1406. Min Act: -0.1700
Data Index: 2141120 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1406. Min Act: -0.1700
Data Index: 2381710 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1230. Min Act: -0.1700
Data Index: 2729147 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1230. Min Act: -0.1700
Data Index: 7067859 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1230. Min Act: -0.1700
Data Index: 6197426 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1230. Min Act: -0.1700
Data Index: 5186925 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1055. Min Act: -0.1700
Data Index: 7067864 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1055. Min Act: -0.1700
Data Index: 7067862 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1055. Min Act: -0.1700
Data Index: 4150063 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19