Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5111 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.6161. Min Act: -0.1700
Data Index: 3606901 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.4286. Min Act: -0.1700
Data Index: 5593032 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.3974. Min Act: -0.1700
Data Index: 62683 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.4286. Min Act: -0.1700
Data Index: 2877167 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.4599. Min Act: -0.1700
Data Index: 4677560 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.3974. Min Act: -0.1700
Data Index: 1302309 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.3974. Min Act: -0.1700
Data Index: 6115124 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.3974. Min Act: -0.1700
Data Index: 148820 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.3349. Min Act: -0.1700
Data Index: 5902206 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.3661. Min Act: -0.1700
Data Index: 2877155 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.3661. Min Act: -0.1700
Data Index: 2532230 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.3661. Min Act: -0.1700
Data Index: 3027129 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.3661. Min Act: -0.1700
Data Index: 1981384 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.3349. Min Act: -0.1700
Data Index: 8630301 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.3661. Min Act: -0.1700
Data Index: 4781436 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.3661. Min Act: -0.1700
Data Index: 654759 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.3349. Min Act: -0.1700
Data Index: 1459666 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.3349. Min Act: -0.1700
Data Index: 3299004 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.3349. Min Act: -0.1700
Data Index: 1437723 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.3036. Min Act: -0.1700
Data Index: 5449923 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19