Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6017 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1118. Min Range: -7.1118
Max Act: 7.1118. Min Act: -0.1700
Data Index: 1418354 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1118. Min Range: -7.1118
Max Act: 6.2681. Min Act: -0.1700
Data Index: 2233686 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1118. Min Range: -7.1118
Max Act: 6.1743. Min Act: -0.1700
Data Index: 3326489 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1118. Min Range: -7.1118
Max Act: 6.0493. Min Act: -0.1700
Data Index: 3887444 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1118. Min Range: -7.1118
Max Act: 5.9243. Min Act: -0.1700
Data Index: 1193763 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1118. Min Range: -7.1118
Max Act: 5.8618. Min Act: -0.1700
Data Index: 3275967 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1118. Min Range: -7.1118
Max Act: 5.7993. Min Act: -0.1700
Data Index: 8789559 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1118. Min Range: -7.1118
Max Act: 5.8306. Min Act: -0.1700
Data Index: 1593968 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1118. Min Range: -7.1118
Max Act: 5.7993. Min Act: -0.1700
Data Index: 6326386 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1118. Min Range: -7.1118
Max Act: 5.7368. Min Act: -0.1700
Data Index: 5106006 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1118. Min Range: -7.1118
Max Act: 5.7368. Min Act: -0.1700
Data Index: 1703316 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1118. Min Range: -7.1118
Max Act: 5.7681. Min Act: -0.1700
Data Index: 3791599 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1118. Min Range: -7.1118
Max Act: 5.7056. Min Act: -0.1700
Data Index: 569694 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1118. Min Range: -7.1118
Max Act: 5.7056. Min Act: -0.1700
Data Index: 200852 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1118. Min Range: -7.1118
Max Act: 5.7368. Min Act: -0.1700
Data Index: 2040233 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1118. Min Range: -7.1118
Max Act: 5.6743. Min Act: -0.1700
Data Index: 5778307 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1118. Min Range: -7.1118
Max Act: 5.6743. Min Act: -0.1700
Data Index: 2377349 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1118. Min Range: -7.1118
Max Act: 5.6743. Min Act: -0.1700
Data Index: 7520536 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1118. Min Range: -7.1118
Max Act: 5.6431. Min Act: -0.1700
Data Index: 6160574 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1118. Min Range: -7.1118
Max Act: 5.6431. Min Act: -0.1700
Data Index: 4827405 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19