Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2551. Min Range: -5.2551
Max Act: 5.2551. Min Act: -0.1700
Data Index: 2547318 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2551. Min Range: -5.2551
Max Act: 5.2551. Min Act: -0.1700
Data Index: 4936099 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2551. Min Range: -5.2551
Max Act: 5.1614. Min Act: -0.1700
Data Index: 3887114 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2551. Min Range: -5.2551
Max Act: 5.1614. Min Act: -0.1700
Data Index: 4186829 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2551. Min Range: -5.2551
Max Act: 5.1301. Min Act: -0.1700
Data Index: 384543 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2551. Min Range: -5.2551
Max Act: 5.1301. Min Act: -0.1700
Data Index: 4610701 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2551. Min Range: -5.2551
Max Act: 5.0989. Min Act: -0.1700
Data Index: 5144637 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2551. Min Range: -5.2551
Max Act: 5.0989. Min Act: -0.1700
Data Index: 4840540 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2551. Min Range: -5.2551
Max Act: 5.0676. Min Act: -0.1700
Data Index: 7024819 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2551. Min Range: -5.2551
Max Act: 5.0364. Min Act: -0.1700
Data Index: 5215626 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2551. Min Range: -5.2551
Max Act: 5.0676. Min Act: -0.1700
Data Index: 4114033 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2551. Min Range: -5.2551
Max Act: 5.0364. Min Act: -0.1700
Data Index: 1065806 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2551. Min Range: -5.2551
Max Act: 5.0364. Min Act: -0.1700
Data Index: 2487338 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2551. Min Range: -5.2551
Max Act: 5.0364. Min Act: -0.1700
Data Index: 1498936 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2551. Min Range: -5.2551
Max Act: 5.0051. Min Act: -0.1700
Data Index: 5050666 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2551. Min Range: -5.2551
Max Act: 5.0364. Min Act: -0.1700
Data Index: 8467835 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2551. Min Range: -5.2551
Max Act: 5.0364. Min Act: -0.1700
Data Index: 4070504 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2551. Min Range: -5.2551
Max Act: 5.0364. Min Act: -0.1700
Data Index: 7601033 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2551. Min Range: -5.2551
Max Act: 4.9739. Min Act: -0.1700
Data Index: 2315077 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2551. Min Range: -5.2551
Max Act: 5.0051. Min Act: -0.1700
Data Index: 1066760 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19