Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2018 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6875. Min Range: -2.6875
Max Act: 2.6875. Min Act: -0.1700
Data Index: 4339565 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6875. Min Range: -2.6875
Max Act: 2.6394. Min Act: -0.1700
Data Index: 4408455 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6875. Min Range: -2.6875
Max Act: 2.5589. Min Act: -0.1700
Data Index: 4284837 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6875. Min Range: -2.6875
Max Act: 2.5428. Min Act: -0.1700
Data Index: 6051303 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6875. Min Range: -2.6875
Max Act: 2.5428. Min Act: -0.1700
Data Index: 555229 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6875. Min Range: -2.6875
Max Act: 2.5266. Min Act: -0.1700
Data Index: 6757257 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6875. Min Range: -2.6875
Max Act: 2.5266. Min Act: -0.1700
Data Index: 7067518 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6875. Min Range: -2.6875
Max Act: 2.5266. Min Act: -0.1700
Data Index: 7366659 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6875. Min Range: -2.6875
Max Act: 2.5104. Min Act: -0.1700
Data Index: 441553 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6875. Min Range: -2.6875
Max Act: 2.5104. Min Act: -0.1700
Data Index: 1204235 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6875. Min Range: -2.6875
Max Act: 2.5104. Min Act: -0.1700
Data Index: 7303452 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6875. Min Range: -2.6875
Max Act: 2.4942. Min Act: -0.1700
Data Index: 7838774 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6875. Min Range: -2.6875
Max Act: 2.4780. Min Act: -0.1700
Data Index: 8323800 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6875. Min Range: -2.6875
Max Act: 2.5104. Min Act: -0.1700
Data Index: 4598785 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6875. Min Range: -2.6875
Max Act: 2.4618. Min Act: -0.1700
Data Index: 4767631 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6875. Min Range: -2.6875
Max Act: 2.4780. Min Act: -0.1700
Data Index: 6330294 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6875. Min Range: -2.6875
Max Act: 2.4618. Min Act: -0.1700
Data Index: 2927011 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6875. Min Range: -2.6875
Max Act: 2.4780. Min Act: -0.1700
Data Index: 2887521 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6875. Min Range: -2.6875
Max Act: 2.4780. Min Act: -0.1700
Data Index: 3890014 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6875. Min Range: -2.6875
Max Act: 2.4780. Min Act: -0.1700
Data Index: 4542780 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19