Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3599 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.5442. Min Act: -0.1700
Data Index: 4381131 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.4817. Min Act: -0.1700
Data Index: 3150095 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.5442. Min Act: -0.1700
Data Index: 5457743 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.5129. Min Act: -0.1700
Data Index: 606560 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.4504. Min Act: -0.1700
Data Index: 1995260 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.4504. Min Act: -0.1700
Data Index: 4183675 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.4192. Min Act: -0.1700
Data Index: 8054064 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.4192. Min Act: -0.1700
Data Index: 262139 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.4192. Min Act: -0.1700
Data Index: 527492 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.3567. Min Act: -0.1700
Data Index: 6698348 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.4192. Min Act: -0.1700
Data Index: 5456011 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.3567. Min Act: -0.1700
Data Index: 2962913 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.3254. Min Act: -0.1700
Data Index: 989674 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.3567. Min Act: -0.1700
Data Index: 3763681 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.3254. Min Act: -0.1700
Data Index: 1388735 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.3567. Min Act: -0.1700
Data Index: 993345 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.3567. Min Act: -0.1700
Data Index: 3062737 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.3567. Min Act: -0.1700
Data Index: 711661 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.3254. Min Act: -0.1700
Data Index: 2511347 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.2942. Min Act: -0.1700
Data Index: 1364088 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19