Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 792 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7913. Min Range: -5.7913
Max Act: 5.7913. Min Act: -0.1700
Data Index: 2351285 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7913. Min Range: -5.7913
Max Act: 5.6975. Min Act: -0.1700
Data Index: 200275 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7913. Min Range: -5.7913
Max Act: 5.6663. Min Act: -0.1700
Data Index: 4589997 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7913. Min Range: -5.7913
Max Act: 5.6038. Min Act: -0.1700
Data Index: 7762721 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7913. Min Range: -5.7913
Max Act: 5.5100. Min Act: -0.1700
Data Index: 4028074 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7913. Min Range: -5.7913
Max Act: 5.4475. Min Act: -0.1700
Data Index: 6538725 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7913. Min Range: -5.7913
Max Act: 5.4163. Min Act: -0.1700
Data Index: 7729126 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7913. Min Range: -5.7913
Max Act: 5.4163. Min Act: -0.1700
Data Index: 2703587 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7913. Min Range: -5.7913
Max Act: 5.4475. Min Act: -0.1700
Data Index: 4202233 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7913. Min Range: -5.7913
Max Act: 5.3538. Min Act: -0.1700
Data Index: 8490890 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7913. Min Range: -5.7913
Max Act: 5.2913. Min Act: -0.1700
Data Index: 4193935 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7913. Min Range: -5.7913
Max Act: 5.2913. Min Act: -0.1700
Data Index: 7839659 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7913. Min Range: -5.7913
Max Act: 5.2913. Min Act: -0.1700
Data Index: 5694108 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7913. Min Range: -5.7913
Max Act: 5.1975. Min Act: -0.1700
Data Index: 625195 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7913. Min Range: -5.7913
Max Act: 5.1975. Min Act: -0.1700
Data Index: 5983904 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7913. Min Range: -5.7913
Max Act: 5.1975. Min Act: -0.1700
Data Index: 3041991 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7913. Min Range: -5.7913
Max Act: 5.1975. Min Act: -0.1700
Data Index: 8237325 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7913. Min Range: -5.7913
Max Act: 5.1975. Min Act: -0.1700
Data Index: 1860353 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7913. Min Range: -5.7913
Max Act: 5.1663. Min Act: -0.1700
Data Index: 4433101 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7913. Min Range: -5.7913
Max Act: 5.1663. Min Act: -0.1700
Data Index: 5761916 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19