Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6397 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5663. Min Range: -6.5663
Max Act: 6.5663. Min Act: -0.1700
Data Index: 959784 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5663. Min Range: -6.5663
Max Act: 6.4725. Min Act: -0.1700
Data Index: 3544351 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5663. Min Range: -6.5663
Max Act: 6.4413. Min Act: -0.1700
Data Index: 4996827 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5663. Min Range: -6.5663
Max Act: 6.3788. Min Act: -0.1700
Data Index: 785072 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5663. Min Range: -6.5663
Max Act: 6.4100. Min Act: -0.1700
Data Index: 808349 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5663. Min Range: -6.5663
Max Act: 6.3475. Min Act: -0.1700
Data Index: 1788890 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5663. Min Range: -6.5663
Max Act: 6.3475. Min Act: -0.1700
Data Index: 6446734 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5663. Min Range: -6.5663
Max Act: 6.3475. Min Act: -0.1700
Data Index: 1703421 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5663. Min Range: -6.5663
Max Act: 6.3163. Min Act: -0.1700
Data Index: 8530768 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5663. Min Range: -6.5663
Max Act: 6.3163. Min Act: -0.1700
Data Index: 3988621 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5663. Min Range: -6.5663
Max Act: 6.3163. Min Act: -0.1700
Data Index: 6813596 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5663. Min Range: -6.5663
Max Act: 6.3163. Min Act: -0.1700
Data Index: 3190528 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5663. Min Range: -6.5663
Max Act: 6.2850. Min Act: -0.1700
Data Index: 1163551 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5663. Min Range: -6.5663
Max Act: 6.2850. Min Act: -0.1700
Data Index: 6634530 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5663. Min Range: -6.5663
Max Act: 6.2850. Min Act: -0.1700
Data Index: 3255880 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5663. Min Range: -6.5663
Max Act: 6.2850. Min Act: -0.1700
Data Index: 5439276 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5663. Min Range: -6.5663
Max Act: 6.2850. Min Act: -0.1700
Data Index: 7750328 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5663. Min Range: -6.5663
Max Act: 6.2538. Min Act: -0.1700
Data Index: 4228693 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5663. Min Range: -6.5663
Max Act: 6.2850. Min Act: -0.1700
Data Index: 6561173 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5663. Min Range: -6.5663
Max Act: 6.2850. Min Act: -0.1700
Data Index: 6602709 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19