Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2833 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9862. Min Range: -3.9862
Max Act: 3.9862. Min Act: -0.1700
Data Index: 455815 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9862. Min Range: -3.9862
Max Act: 3.9550. Min Act: -0.1700
Data Index: 5091 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9862. Min Range: -3.9862
Max Act: 3.9237. Min Act: -0.1700
Data Index: 2771279 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9862. Min Range: -3.9862
Max Act: 3.9237. Min Act: -0.1700
Data Index: 7875734 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9862. Min Range: -3.9862
Max Act: 3.8924. Min Act: -0.1700
Data Index: 2301363 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9862. Min Range: -3.9862
Max Act: 3.8924. Min Act: -0.1700
Data Index: 4059375 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9862. Min Range: -3.9862
Max Act: 3.8924. Min Act: -0.1700
Data Index: 4159406 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9862. Min Range: -3.9862
Max Act: 3.8924. Min Act: -0.1700
Data Index: 649941 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9862. Min Range: -3.9862
Max Act: 3.8612. Min Act: -0.1700
Data Index: 1094967 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9862. Min Range: -3.9862
Max Act: 3.8612. Min Act: -0.1700
Data Index: 224828 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9862. Min Range: -3.9862
Max Act: 3.8612. Min Act: -0.1700
Data Index: 969561 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9862. Min Range: -3.9862
Max Act: 3.8612. Min Act: -0.1700
Data Index: 956794 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9862. Min Range: -3.9862
Max Act: 3.8612. Min Act: -0.1700
Data Index: 783748 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9862. Min Range: -3.9862
Max Act: 3.8612. Min Act: -0.1700
Data Index: 430048 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9862. Min Range: -3.9862
Max Act: 3.8612. Min Act: -0.1700
Data Index: 141768 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9862. Min Range: -3.9862
Max Act: 3.8612. Min Act: -0.1700
Data Index: 412313 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9862. Min Range: -3.9862
Max Act: 3.8612. Min Act: -0.1700
Data Index: 393087 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9862. Min Range: -3.9862
Max Act: 3.8612. Min Act: -0.1700
Data Index: 119283 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9862. Min Range: -3.9862
Max Act: 3.8612. Min Act: -0.1700
Data Index: 174309 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9862. Min Range: -3.9862
Max Act: 3.8612. Min Act: -0.1700
Data Index: 732843 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19