Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2008 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9160. Min Range: -3.9160
Max Act: 3.9160. Min Act: -0.1700
Data Index: 3996907 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9160. Min Range: -3.9160
Max Act: 3.8691. Min Act: -0.1700
Data Index: 7695134 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9160. Min Range: -3.9160
Max Act: 3.7596. Min Act: -0.1700
Data Index: 6162081 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9160. Min Range: -3.9160
Max Act: 3.7283. Min Act: -0.1700
Data Index: 3620626 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9160. Min Range: -3.9160
Max Act: 3.7440. Min Act: -0.1700
Data Index: 5921854 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9160. Min Range: -3.9160
Max Act: 3.7283. Min Act: -0.1700
Data Index: 1218449 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9160. Min Range: -3.9160
Max Act: 3.7127. Min Act: -0.1700
Data Index: 7467143 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9160. Min Range: -3.9160
Max Act: 3.7127. Min Act: -0.1700
Data Index: 5484331 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9160. Min Range: -3.9160
Max Act: 3.7283. Min Act: -0.1700
Data Index: 1638589 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9160. Min Range: -3.9160
Max Act: 3.6971. Min Act: -0.1700
Data Index: 5746699 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9160. Min Range: -3.9160
Max Act: 3.7127. Min Act: -0.1700
Data Index: 1428440 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9160. Min Range: -3.9160
Max Act: 3.6971. Min Act: -0.1700
Data Index: 1258982 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9160. Min Range: -3.9160
Max Act: 3.6814. Min Act: -0.1700
Data Index: 7540094 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9160. Min Range: -3.9160
Max Act: 3.6814. Min Act: -0.1700
Data Index: 4833449 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9160. Min Range: -3.9160
Max Act: 3.6188. Min Act: -0.1700
Data Index: 4714955 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9160. Min Range: -3.9160
Max Act: 3.6188. Min Act: -0.1700
Data Index: 1333621 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9160. Min Range: -3.9160
Max Act: 3.6188. Min Act: -0.1700
Data Index: 8798493 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9160. Min Range: -3.9160
Max Act: 3.6188. Min Act: -0.1700
Data Index: 4773981 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9160. Min Range: -3.9160
Max Act: 3.6188. Min Act: -0.1700
Data Index: 986158 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9160. Min Range: -3.9160
Max Act: 3.6032. Min Act: -0.1700
Data Index: 130515 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19