Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.4363. Min Act: -0.1700
Data Index: 3845190 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.4050. Min Act: -0.1700
Data Index: 7327581 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2488. Min Act: -0.1700
Data Index: 990662 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2488. Min Act: -0.1700
Data Index: 3205751 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2175. Min Act: -0.1700
Data Index: 941671 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2175. Min Act: -0.1700
Data Index: 2237408 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1863. Min Act: -0.1700
Data Index: 5836937 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1863. Min Act: -0.1700
Data Index: 5427998 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1863. Min Act: -0.1700
Data Index: 4261338 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1863. Min Act: -0.1700
Data Index: 3748048 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1863. Min Act: -0.1700
Data Index: 1527169 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1550. Min Act: -0.1699
Data Index: 4357887 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1550. Min Act: -0.1700
Data Index: 7327582 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1238. Min Act: -0.1700
Data Index: 4924113 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.0925. Min Act: -0.1700
Data Index: 7801312 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.0613. Min Act: -0.1700
Data Index: 7861642 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1238. Min Act: -0.1700
Data Index: 4606843 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.0613. Min Act: -0.1700
Data Index: 191902 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.0613. Min Act: -0.1700
Data Index: 3028549 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.0613. Min Act: -0.1700
Data Index: 869221 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19