Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 565 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0351. Min Range: -8.0351
Max Act: 8.0351. Min Act: -0.1700
Data Index: 2892103 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.8476. Min Act: -0.1700
Data Index: 8750734 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.7226. Min Act: -0.1700
Data Index: 8395259 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.6288. Min Act: -0.1700
Data Index: 6685430 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.7226. Min Act: -0.1700
Data Index: 2251570 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.6288. Min Act: -0.1700
Data Index: 3543839 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.4413. Min Act: -0.1700
Data Index: 6183289 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.4101. Min Act: -0.1700
Data Index: 3732118 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.4101. Min Act: -0.1700
Data Index: 3455268 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.3788. Min Act: -0.1700
Data Index: 6896990 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.3788. Min Act: -0.1700
Data Index: 6161311 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.3476. Min Act: -0.1700
Data Index: 6857432 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.2851. Min Act: -0.1700
Data Index: 2834521 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.2226. Min Act: -0.1700
Data Index: 7676596 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.2538. Min Act: -0.1700
Data Index: 3623045 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.2226. Min Act: -0.1700
Data Index: 4128711 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.2226. Min Act: -0.1700
Data Index: 8219822 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.1288. Min Act: -0.1700
Data Index: 7801709 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.1288. Min Act: -0.1700
Data Index: 4117078 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0351. Min Range: -8.0351
Max Act: 7.1288. Min Act: -0.1700
Data Index: 6353627 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19