Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2485 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0316. Min Range: -7.0316
Max Act: 7.0316. Min Act: -0.1700
Data Index: 5995713 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0316. Min Range: -7.0316
Max Act: 6.7503. Min Act: -0.1700
Data Index: 2340741 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0316. Min Range: -7.0316
Max Act: 6.7503. Min Act: -0.1700
Data Index: 108095 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0316. Min Range: -7.0316
Max Act: 6.7503. Min Act: -0.1700
Data Index: 5794556 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0316. Min Range: -7.0316
Max Act: 6.7191. Min Act: -0.1700
Data Index: 8045869 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0316. Min Range: -7.0316
Max Act: 6.6566. Min Act: -0.1700
Data Index: 6578619 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0316. Min Range: -7.0316
Max Act: 6.6878. Min Act: -0.1700
Data Index: 4736128 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0316. Min Range: -7.0316
Max Act: 6.6253. Min Act: -0.1700
Data Index: 2175137 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0316. Min Range: -7.0316
Max Act: 6.5941. Min Act: -0.1700
Data Index: 1666111 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0316. Min Range: -7.0316
Max Act: 6.5941. Min Act: -0.1700
Data Index: 2499670 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0316. Min Range: -7.0316
Max Act: 6.5628. Min Act: -0.1700
Data Index: 5140435 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0316. Min Range: -7.0316
Max Act: 6.5316. Min Act: -0.1700
Data Index: 3962006 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0316. Min Range: -7.0316
Max Act: 6.6253. Min Act: -0.1700
Data Index: 6837365 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0316. Min Range: -7.0316
Max Act: 6.5316. Min Act: -0.1700
Data Index: 5543996 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0316. Min Range: -7.0316
Max Act: 6.5941. Min Act: -0.1700
Data Index: 7508941 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0316. Min Range: -7.0316
Max Act: 6.5316. Min Act: -0.1700
Data Index: 1685295 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0316. Min Range: -7.0316
Max Act: 6.5316. Min Act: -0.1700
Data Index: 1966973 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0316. Min Range: -7.0316
Max Act: 6.5316. Min Act: -0.1700
Data Index: 916418 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0316. Min Range: -7.0316
Max Act: 6.5003. Min Act: -0.1700
Data Index: 5670879 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0316. Min Range: -7.0316
Max Act: 6.5003. Min Act: -0.1700
Data Index: 2236290 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19