Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2766 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3946. Min Range: -6.3946
Max Act: 6.3946. Min Act: -0.1700
Data Index: 4357330 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3946. Min Range: -6.3946
Max Act: 6.2071. Min Act: -0.1700
Data Index: 3310198 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3946. Min Range: -6.3946
Max Act: 5.8946. Min Act: -0.1700
Data Index: 5307546 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3946. Min Range: -6.3946
Max Act: 5.8946. Min Act: -0.1700
Data Index: 8273362 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3946. Min Range: -6.3946
Max Act: 5.8634. Min Act: -0.1700
Data Index: 5870069 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3946. Min Range: -6.3946
Max Act: 5.8634. Min Act: -0.1700
Data Index: 3610134 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3946. Min Range: -6.3946
Max Act: 5.8634. Min Act: -0.1700
Data Index: 7000235 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3946. Min Range: -6.3946
Max Act: 5.8321. Min Act: -0.1700
Data Index: 8497883 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3946. Min Range: -6.3946
Max Act: 5.8009. Min Act: -0.1700
Data Index: 2401588 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3946. Min Range: -6.3946
Max Act: 5.8009. Min Act: -0.1700
Data Index: 2161610 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3946. Min Range: -6.3946
Max Act: 5.7696. Min Act: -0.1700
Data Index: 5156926 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3946. Min Range: -6.3946
Max Act: 5.7384. Min Act: -0.1700
Data Index: 8150823 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3946. Min Range: -6.3946
Max Act: 5.7384. Min Act: -0.1700
Data Index: 5858131 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3946. Min Range: -6.3946
Max Act: 5.6759. Min Act: -0.1700
Data Index: 7602121 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3946. Min Range: -6.3946
Max Act: 5.6759. Min Act: -0.1700
Data Index: 3535539 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3946. Min Range: -6.3946
Max Act: 5.7071. Min Act: -0.1700
Data Index: 736646 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3946. Min Range: -6.3946
Max Act: 5.7071. Min Act: -0.1700
Data Index: 552747 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3946. Min Range: -6.3946
Max Act: 5.7071. Min Act: -0.1700
Data Index: 3990556 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3946. Min Range: -6.3946
Max Act: 5.7071. Min Act: -0.1700
Data Index: 4630121 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3946. Min Range: -6.3946
Max Act: 5.6759. Min Act: -0.1700
Data Index: 2234640 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19