Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1295 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4670. Min Range: -4.4670
Max Act: 4.4670. Min Act: -0.1700
Data Index: 471309 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4670. Min Range: -4.4670
Max Act: 4.4670. Min Act: -0.1700
Data Index: 1185260 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4670. Min Range: -4.4670
Max Act: 4.4670. Min Act: -0.1700
Data Index: 495535 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4670. Min Range: -4.4670
Max Act: 4.4358. Min Act: -0.1700
Data Index: 928695 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4670. Min Range: -4.4670
Max Act: 4.4358. Min Act: -0.1700
Data Index: 3416340 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4670. Min Range: -4.4670
Max Act: 4.4358. Min Act: -0.1700
Data Index: 3986869 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4670. Min Range: -4.4670
Max Act: 4.4358. Min Act: -0.1700
Data Index: 4812630 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4670. Min Range: -4.4670
Max Act: 4.4045. Min Act: -0.1700
Data Index: 2908515 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4670. Min Range: -4.4670
Max Act: 4.4045. Min Act: -0.1700
Data Index: 8795183 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4670. Min Range: -4.4670
Max Act: 4.4045. Min Act: -0.1700
Data Index: 7703246 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4670. Min Range: -4.4670
Max Act: 4.4045. Min Act: -0.1700
Data Index: 7293213 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4670. Min Range: -4.4670
Max Act: 4.4045. Min Act: -0.1699
Data Index: 7208271 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4670. Min Range: -4.4670
Max Act: 4.4045. Min Act: -0.1700
Data Index: 6166105 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4670. Min Range: -4.4670
Max Act: 4.4045. Min Act: -0.1700
Data Index: 1336385 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4670. Min Range: -4.4670
Max Act: 4.4045. Min Act: -0.1700
Data Index: 1281602 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4670. Min Range: -4.4670
Max Act: 4.4045. Min Act: -0.1700
Data Index: 1605838 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4670. Min Range: -4.4670
Max Act: 4.4045. Min Act: -0.1700
Data Index: 471852 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4670. Min Range: -4.4670
Max Act: 4.4045. Min Act: -0.1700
Data Index: 2495603 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4670. Min Range: -4.4670
Max Act: 4.3733. Min Act: -0.1700
Data Index: 2470019 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4670. Min Range: -4.4670
Max Act: 4.3733. Min Act: -0.1700
Data Index: 362765 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19