Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3211 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7125. Min Range: -5.7125
Max Act: 5.6500. Min Act: -0.1700
Data Index: 141608 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7125. Min Range: -5.7125
Max Act: 5.7125. Min Act: -0.1700
Data Index: 4697604 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7125. Min Range: -5.7125
Max Act: 5.6188. Min Act: -0.1700
Data Index: 7694515 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7125. Min Range: -5.7125
Max Act: 5.6188. Min Act: -0.1700
Data Index: 6725651 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7125. Min Range: -5.7125
Max Act: 5.6188. Min Act: -0.1700
Data Index: 5767364 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7125. Min Range: -5.7125
Max Act: 5.5875. Min Act: -0.1700
Data Index: 5467004 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7125. Min Range: -5.7125
Max Act: 5.5875. Min Act: -0.1700
Data Index: 3735995 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7125. Min Range: -5.7125
Max Act: 5.5875. Min Act: -0.1700
Data Index: 2213595 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7125. Min Range: -5.7125
Max Act: 5.5875. Min Act: -0.1700
Data Index: 8737818 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7125. Min Range: -5.7125
Max Act: 5.5563. Min Act: -0.1700
Data Index: 5923553 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7125. Min Range: -5.7125
Max Act: 5.5875. Min Act: -0.1700
Data Index: 1860829 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7125. Min Range: -5.7125
Max Act: 5.5250. Min Act: -0.1700
Data Index: 7916183 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7125. Min Range: -5.7125
Max Act: 5.4938. Min Act: -0.1700
Data Index: 7995545 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7125. Min Range: -5.7125
Max Act: 5.4625. Min Act: -0.1700
Data Index: 1140335 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7125. Min Range: -5.7125
Max Act: 5.4625. Min Act: -0.1700
Data Index: 6797082 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7125. Min Range: -5.7125
Max Act: 5.4313. Min Act: -0.1700
Data Index: 3459739 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7125. Min Range: -5.7125
Max Act: 5.4313. Min Act: -0.1700
Data Index: 8832603 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7125. Min Range: -5.7125
Max Act: 5.3688. Min Act: -0.1700
Data Index: 2596433 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7125. Min Range: -5.7125
Max Act: 5.3688. Min Act: -0.1700
Data Index: 4199295 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7125. Min Range: -5.7125
Max Act: 5.4000. Min Act: -0.1700
Data Index: 7612586 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19