Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4371 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7055. Min Range: -3.7055
Max Act: 3.7055. Min Act: -0.1700
Data Index: 2970413 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7055. Min Range: -3.7055
Max Act: 3.6742. Min Act: -0.1700
Data Index: 5437904 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7055. Min Range: -3.7055
Max Act: 3.7055. Min Act: -0.1700
Data Index: 3721333 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7055. Min Range: -3.7055
Max Act: 3.7055. Min Act: -0.1700
Data Index: 7797945 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7055. Min Range: -3.7055
Max Act: 3.6742. Min Act: -0.1700
Data Index: 538181 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7055. Min Range: -3.7055
Max Act: 3.6742. Min Act: -0.1700
Data Index: 6645480 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7055. Min Range: -3.7055
Max Act: 3.6742. Min Act: -0.1700
Data Index: 6383957 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7055. Min Range: -3.7055
Max Act: 3.6742. Min Act: -0.1700
Data Index: 8318004 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7055. Min Range: -3.7055
Max Act: 3.6742. Min Act: -0.1700
Data Index: 8288274 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7055. Min Range: -3.7055
Max Act: 3.6742. Min Act: -0.1700
Data Index: 5410437 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7055. Min Range: -3.7055
Max Act: 3.6742. Min Act: -0.1700
Data Index: 7822351 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7055. Min Range: -3.7055
Max Act: 3.6430. Min Act: -0.1700
Data Index: 1289591 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7055. Min Range: -3.7055
Max Act: 3.6742. Min Act: -0.1700
Data Index: 207400 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7055. Min Range: -3.7055
Max Act: 3.6742. Min Act: -0.1700
Data Index: 2996166 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7055. Min Range: -3.7055
Max Act: 3.6742. Min Act: -0.1700
Data Index: 2799875 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7055. Min Range: -3.7055
Max Act: 3.6742. Min Act: -0.1700
Data Index: 2667375 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7055. Min Range: -3.7055
Max Act: 3.6742. Min Act: -0.1700
Data Index: 1094210 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7055. Min Range: -3.7055
Max Act: 3.6742. Min Act: -0.1700
Data Index: 2571462 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7055. Min Range: -3.7055
Max Act: 3.6430. Min Act: -0.1700
Data Index: 6737917 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7055. Min Range: -3.7055
Max Act: 3.6117. Min Act: -0.1700
Data Index: 6920543 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19