Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1848 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1201. Min Range: -3.1201
Max Act: 3.1201. Min Act: -0.1700
Data Index: 4020050 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1201. Min Range: -3.1201
Max Act: 3.0886. Min Act: -0.1700
Data Index: 4933427 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1201. Min Range: -3.1201
Max Act: 3.0886. Min Act: -0.1700
Data Index: 6010963 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1201. Min Range: -3.1201
Max Act: 3.0728. Min Act: -0.1700
Data Index: 1902423 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1201. Min Range: -3.1201
Max Act: 3.0571. Min Act: -0.1700
Data Index: 288090 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1201. Min Range: -3.1201
Max Act: 3.0255. Min Act: -0.1700
Data Index: 1068446 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1201. Min Range: -3.1201
Max Act: 3.0255. Min Act: -0.1700
Data Index: 1629032 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1201. Min Range: -3.1201
Max Act: 3.0255. Min Act: -0.1700
Data Index: 5222941 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1201. Min Range: -3.1201
Max Act: 3.0255. Min Act: -0.1700
Data Index: 1682264 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1201. Min Range: -3.1201
Max Act: 3.0097. Min Act: -0.1700
Data Index: 200388 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1201. Min Range: -3.1201
Max Act: 3.0097. Min Act: -0.1700
Data Index: 7939123 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1201. Min Range: -3.1201
Max Act: 3.0097. Min Act: -0.1700
Data Index: 4586940 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1201. Min Range: -3.1201
Max Act: 2.9939. Min Act: -0.1700
Data Index: 3498216 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1201. Min Range: -3.1201
Max Act: 3.0097. Min Act: -0.1700
Data Index: 2356924 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1201. Min Range: -3.1201
Max Act: 2.9939. Min Act: -0.1700
Data Index: 8530220 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1201. Min Range: -3.1201
Max Act: 2.9939. Min Act: -0.1700
Data Index: 4330691 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1201. Min Range: -3.1201
Max Act: 2.9306. Min Act: -0.1700
Data Index: 8600764 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1201. Min Range: -3.1201
Max Act: 2.9464. Min Act: -0.1700
Data Index: 7886185 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1201. Min Range: -3.1201
Max Act: 2.9464. Min Act: -0.1700
Data Index: 7607059 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1201. Min Range: -3.1201
Max Act: 2.9464. Min Act: -0.1700
Data Index: 3558434 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19