Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5075 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4798. Min Range: -3.4798
Max Act: 3.4798. Min Act: -0.1700
Data Index: 532738 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4798. Min Range: -3.4798
Max Act: 3.3857. Min Act: -0.1700
Data Index: 6011994 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4798. Min Range: -3.4798
Max Act: 3.3857. Min Act: -0.1700
Data Index: 4671316 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4798. Min Range: -3.4798
Max Act: 3.3387. Min Act: -0.1700
Data Index: 5770991 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4798. Min Range: -3.4798
Max Act: 3.3230. Min Act: -0.1700
Data Index: 8197479 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4798. Min Range: -3.4798
Max Act: 3.3230. Min Act: -0.1700
Data Index: 1576687 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4798. Min Range: -3.4798
Max Act: 3.3230. Min Act: -0.1700
Data Index: 1308428 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4798. Min Range: -3.4798
Max Act: 3.3230. Min Act: -0.1700
Data Index: 2151841 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4798. Min Range: -3.4798
Max Act: 3.3073. Min Act: -0.1700
Data Index: 7247588 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4798. Min Range: -3.4798
Max Act: 3.2916. Min Act: -0.1700
Data Index: 3963709 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4798. Min Range: -3.4798
Max Act: 3.3073. Min Act: -0.1700
Data Index: 4001991 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4798. Min Range: -3.4798
Max Act: 3.3073. Min Act: -0.1700
Data Index: 3562216 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4798. Min Range: -3.4798
Max Act: 3.3073. Min Act: -0.1700
Data Index: 4812597 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4798. Min Range: -3.4798
Max Act: 3.2916. Min Act: -0.1700
Data Index: 7024166 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4798. Min Range: -3.4798
Max Act: 3.2916. Min Act: -0.1700
Data Index: 7510831 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4798. Min Range: -3.4798
Max Act: 3.2759. Min Act: -0.1700
Data Index: 242014 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4798. Min Range: -3.4798
Max Act: 3.2916. Min Act: -0.1700
Data Index: 2766088 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4798. Min Range: -3.4798
Max Act: 3.2916. Min Act: -0.1700
Data Index: 8363579 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4798. Min Range: -3.4798
Max Act: 3.2916. Min Act: -0.1700
Data Index: 4250914 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4798. Min Range: -3.4798
Max Act: 3.2916. Min Act: -0.1700
Data Index: 8376733 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19