Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 690 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6787. Min Range: -3.6787
Max Act: 3.6787. Min Act: -0.1700
Data Index: 2573723 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6787. Min Range: -3.6787
Max Act: 3.6474. Min Act: -0.1700
Data Index: 8604490 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6787. Min Range: -3.6787
Max Act: 3.6161. Min Act: -0.1700
Data Index: 8128963 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6787. Min Range: -3.6787
Max Act: 3.5535. Min Act: -0.1700
Data Index: 2573728 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6787. Min Range: -3.6787
Max Act: 3.4908. Min Act: -0.1700
Data Index: 5297596 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6787. Min Range: -3.6787
Max Act: 3.4595. Min Act: -0.1700
Data Index: 8824905 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6787. Min Range: -3.6787
Max Act: 3.4595. Min Act: -0.1700
Data Index: 4091832 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6787. Min Range: -3.6787
Max Act: 3.4281. Min Act: -0.1700
Data Index: 6744740 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6787. Min Range: -3.6787
Max Act: 3.4281. Min Act: -0.1700
Data Index: 7373017 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6787. Min Range: -3.6787
Max Act: 3.4281. Min Act: -0.1700
Data Index: 7407492 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6787. Min Range: -3.6787
Max Act: 3.4281. Min Act: -0.1700
Data Index: 5789084 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6787. Min Range: -3.6787
Max Act: 3.4281. Min Act: -0.1700
Data Index: 5277433 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6787. Min Range: -3.6787
Max Act: 3.4281. Min Act: -0.1700
Data Index: 1697590 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6787. Min Range: -3.6787
Max Act: 3.3968. Min Act: -0.1700
Data Index: 784162 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6787. Min Range: -3.6787
Max Act: 3.3968. Min Act: -0.1700
Data Index: 348517 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6787. Min Range: -3.6787
Max Act: 3.3654. Min Act: -0.1700
Data Index: 2535141 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6787. Min Range: -3.6787
Max Act: 3.3968. Min Act: -0.1700
Data Index: 666492 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6787. Min Range: -3.6787
Max Act: 3.3968. Min Act: -0.1700
Data Index: 6097530 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6787. Min Range: -3.6787
Max Act: 3.3968. Min Act: -0.1700
Data Index: 3777729 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6787. Min Range: -3.6787
Max Act: 3.3654. Min Act: -0.1700
Data Index: 608404 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19