Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4290 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.1643. Min Act: -0.1700
Data Index: 4669789 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.1013. Min Act: -0.1700
Data Index: 2623766 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.0698. Min Act: -0.1700
Data Index: 5654079 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.0224. Min Act: -0.1700
Data Index: 6949759 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.0224. Min Act: -0.1700
Data Index: 8030097 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.0066. Min Act: -0.1700
Data Index: 1082118 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.9750. Min Act: -0.1700
Data Index: 900696 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.9592. Min Act: -0.1700
Data Index: 715848 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.8641. Min Act: -0.1700
Data Index: 1925846 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.8482. Min Act: -0.1700
Data Index: 4402394 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.8482. Min Act: -0.1700
Data Index: 2262873 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.8482. Min Act: -0.1700
Data Index: 6505198 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.8323. Min Act: -0.1700
Data Index: 7837002 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.8323. Min Act: -0.1700
Data Index: 7783882 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.8323. Min Act: -0.1700
Data Index: 7814381 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.8164. Min Act: -0.1700
Data Index: 2587524 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.8164. Min Act: -0.1700
Data Index: 4433631 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.8005. Min Act: -0.1700
Data Index: 6021068 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.8005. Min Act: -0.1700
Data Index: 4569323 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.8005. Min Act: -0.1700
Data Index: 4589332 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19