Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5139 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8849. Min Range: -7.8849
Max Act: 7.8849. Min Act: -0.1700
Data Index: 1634423 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8849. Min Range: -7.8849
Max Act: 7.5724. Min Act: -0.1700
Data Index: 4770606 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8849. Min Range: -7.8849
Max Act: 7.4787. Min Act: -0.1700
Data Index: 8209937 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8849. Min Range: -7.8849
Max Act: 7.2912. Min Act: -0.1700
Data Index: 8522800 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8849. Min Range: -7.8849
Max Act: 7.1974. Min Act: -0.1700
Data Index: 831202 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8849. Min Range: -7.8849
Max Act: 7.1974. Min Act: -0.1700
Data Index: 4834092 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8849. Min Range: -7.8849
Max Act: 7.1974. Min Act: -0.1700
Data Index: 6061673 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8849. Min Range: -7.8849
Max Act: 7.1974. Min Act: -0.1700
Data Index: 3709389 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8849. Min Range: -7.8849
Max Act: 7.0724. Min Act: -0.1700
Data Index: 5522933 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8849. Min Range: -7.8849
Max Act: 7.0099. Min Act: -0.1700
Data Index: 7466050 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8849. Min Range: -7.8849
Max Act: 6.9787. Min Act: -0.1700
Data Index: 25717 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8849. Min Range: -7.8849
Max Act: 6.9787. Min Act: -0.1700
Data Index: 6936426 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8849. Min Range: -7.8849
Max Act: 6.9474. Min Act: -0.1700
Data Index: 1684762 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8849. Min Range: -7.8849
Max Act: 6.9162. Min Act: -0.1700
Data Index: 6974248 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8849. Min Range: -7.8849
Max Act: 6.9162. Min Act: -0.1700
Data Index: 6106944 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8849. Min Range: -7.8849
Max Act: 6.8849. Min Act: -0.1700
Data Index: 7275435 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8849. Min Range: -7.8849
Max Act: 6.8849. Min Act: -0.1700
Data Index: 3396971 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8849. Min Range: -7.8849
Max Act: 6.8849. Min Act: -0.1700
Data Index: 7233791 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8849. Min Range: -7.8849
Max Act: 6.8537. Min Act: -0.1700
Data Index: 4030618 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8849. Min Range: -7.8849
Max Act: 6.7912. Min Act: -0.1700
Data Index: 6795190 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19