Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6734. Min Range: -2.6734
Max Act: 2.6734. Min Act: -0.1700
Data Index: 5579749 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6734. Min Range: -2.6734
Max Act: 2.6734. Min Act: -0.1700
Data Index: 8546883 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6734. Min Range: -2.6734
Max Act: 2.6573. Min Act: -0.1700
Data Index: 3824229 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6734. Min Range: -2.6734
Max Act: 2.6413. Min Act: -0.1700
Data Index: 6047147 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6734. Min Range: -2.6734
Max Act: 2.6413. Min Act: -0.1700
Data Index: 4434428 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6734. Min Range: -2.6734
Max Act: 2.6413. Min Act: -0.1700
Data Index: 8199961 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6734. Min Range: -2.6734
Max Act: 2.6091. Min Act: -0.1700
Data Index: 2297972 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6734. Min Range: -2.6734
Max Act: 2.6252. Min Act: -0.1700
Data Index: 2417728 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6734. Min Range: -2.6734
Max Act: 2.6252. Min Act: -0.1700
Data Index: 2300034 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6734. Min Range: -2.6734
Max Act: 2.6252. Min Act: -0.1700
Data Index: 4470084 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6734. Min Range: -2.6734
Max Act: 2.6252. Min Act: -0.1700
Data Index: 469980 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6734. Min Range: -2.6734
Max Act: 2.6252. Min Act: -0.1700
Data Index: 8206572 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6734. Min Range: -2.6734
Max Act: 2.6252. Min Act: -0.1700
Data Index: 6057132 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6734. Min Range: -2.6734
Max Act: 2.6413. Min Act: -0.1700
Data Index: 83311 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6734. Min Range: -2.6734
Max Act: 2.6091. Min Act: -0.1700
Data Index: 8256949 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6734. Min Range: -2.6734
Max Act: 2.6091. Min Act: -0.1700
Data Index: 2000407 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6734. Min Range: -2.6734
Max Act: 2.6091. Min Act: -0.1700
Data Index: 361087 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6734. Min Range: -2.6734
Max Act: 2.6091. Min Act: -0.1700
Data Index: 7147651 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6734. Min Range: -2.6734
Max Act: 2.5930. Min Act: -0.1700
Data Index: 1014193 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6734. Min Range: -2.6734
Max Act: 2.5930. Min Act: -0.1700
Data Index: 6949924 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19