Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 197 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9000. Min Range: -4.9000
Max Act: 4.9000. Min Act: -0.1700
Data Index: 7450899 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9000. Min Range: -4.9000
Max Act: 4.8688. Min Act: -0.1700
Data Index: 4756064 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9000. Min Range: -4.9000
Max Act: 4.8063. Min Act: -0.1700
Data Index: 8796806 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9000. Min Range: -4.9000
Max Act: 4.8063. Min Act: -0.1700
Data Index: 8220696 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9000. Min Range: -4.9000
Max Act: 4.8688. Min Act: -0.1700
Data Index: 2254179 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9000. Min Range: -4.9000
Max Act: 4.7750. Min Act: -0.1700
Data Index: 4108435 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9000. Min Range: -4.9000
Max Act: 4.8063. Min Act: -0.1700
Data Index: 441481 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9000. Min Range: -4.9000
Max Act: 4.7750. Min Act: -0.1700
Data Index: 7209386 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9000. Min Range: -4.9000
Max Act: 4.7750. Min Act: -0.1700
Data Index: 3364786 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9000. Min Range: -4.9000
Max Act: 4.7750. Min Act: -0.1700
Data Index: 2804323 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9000. Min Range: -4.9000
Max Act: 4.7750. Min Act: -0.1700
Data Index: 4399741 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9000. Min Range: -4.9000
Max Act: 4.7438. Min Act: -0.1700
Data Index: 6906939 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9000. Min Range: -4.9000
Max Act: 4.7438. Min Act: -0.1700
Data Index: 6825606 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9000. Min Range: -4.9000
Max Act: 4.7438. Min Act: -0.1700
Data Index: 4475541 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9000. Min Range: -4.9000
Max Act: 4.7438. Min Act: -0.1700
Data Index: 7657384 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9000. Min Range: -4.9000
Max Act: 4.7438. Min Act: -0.1700
Data Index: 6573933 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9000. Min Range: -4.9000
Max Act: 4.7438. Min Act: -0.1700
Data Index: 4263939 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9000. Min Range: -4.9000
Max Act: 4.7438. Min Act: -0.1700
Data Index: 4001502 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9000. Min Range: -4.9000
Max Act: 4.7438. Min Act: -0.1700
Data Index: 3205638 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9000. Min Range: -4.9000
Max Act: 4.7438. Min Act: -0.1700
Data Index: 4170580 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19