Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5670 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7717. Min Range: -4.7717
Max Act: 4.7717. Min Act: -0.1700
Data Index: 5413769 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7717. Min Range: -4.7717
Max Act: 4.0841. Min Act: -0.1700
Data Index: 3881164 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7717. Min Range: -4.7717
Max Act: 4.0529. Min Act: -0.1700
Data Index: 7329190 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7717. Min Range: -4.7717
Max Act: 4.0216. Min Act: -0.1700
Data Index: 5024340 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7717. Min Range: -4.7717
Max Act: 3.9903. Min Act: -0.1700
Data Index: 1739936 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7717. Min Range: -4.7717
Max Act: 3.9591. Min Act: -0.1700
Data Index: 1439356 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7717. Min Range: -4.7717
Max Act: 3.9591. Min Act: -0.1700
Data Index: 4008834 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7717. Min Range: -4.7717
Max Act: 3.9591. Min Act: -0.1700
Data Index: 3766964 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7717. Min Range: -4.7717
Max Act: 3.8965. Min Act: -0.1700
Data Index: 5839761 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7717. Min Range: -4.7717
Max Act: 3.8965. Min Act: -0.1700
Data Index: 8231111 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7717. Min Range: -4.7717
Max Act: 3.8965. Min Act: -0.1700
Data Index: 3122006 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7717. Min Range: -4.7717
Max Act: 3.8965. Min Act: -0.1700
Data Index: 5187396 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7717. Min Range: -4.7717
Max Act: 3.8653. Min Act: -0.1700
Data Index: 8133883 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7717. Min Range: -4.7717
Max Act: 3.8653. Min Act: -0.1700
Data Index: 707835 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7717. Min Range: -4.7717
Max Act: 3.8653. Min Act: -0.1700
Data Index: 817654 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7717. Min Range: -4.7717
Max Act: 3.8653. Min Act: -0.1700
Data Index: 8568320 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7717. Min Range: -4.7717
Max Act: 3.8184. Min Act: -0.1700
Data Index: 2031647 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7717. Min Range: -4.7717
Max Act: 3.8496. Min Act: -0.1700
Data Index: 2511853 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7717. Min Range: -4.7717
Max Act: 3.8496. Min Act: -0.1700
Data Index: 8495061 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7717. Min Range: -4.7717
Max Act: 3.8496. Min Act: -0.1700
Data Index: 5044807 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19