Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3203 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.5738. Min Act: -0.1700
Data Index: 6807385 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.5113. Min Act: -0.1700
Data Index: 2136797 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.5113. Min Act: -0.1700
Data Index: 2012314 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.4800. Min Act: -0.1700
Data Index: 4186818 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.4800. Min Act: -0.1700
Data Index: 8452297 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.4488. Min Act: -0.1700
Data Index: 2606843 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.4488. Min Act: -0.1700
Data Index: 5643761 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.3863. Min Act: -0.1700
Data Index: 2021136 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.3238. Min Act: -0.1700
Data Index: 6608663 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.3238. Min Act: -0.1700
Data Index: 8597500 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.3238. Min Act: -0.1700
Data Index: 6042142 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.3238. Min Act: -0.1700
Data Index: 4579711 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.3238. Min Act: -0.1700
Data Index: 225340 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.2925. Min Act: -0.1700
Data Index: 5822071 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.2925. Min Act: -0.1700
Data Index: 3659210 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.2613. Min Act: -0.1700
Data Index: 7893732 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.3238. Min Act: -0.1700
Data Index: 2886449 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.2925. Min Act: -0.1700
Data Index: 719022 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.2925. Min Act: -0.1700
Data Index: 7143164 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5738. Min Range: -4.5738
Max Act: 4.2613. Min Act: -0.1700
Data Index: 6870826 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19