Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3788 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.5746. Min Range: -1.5746
Max Act: 1.5746. Min Act: -0.1689
Data Index: 4800171 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5746. Min Range: -1.5746
Max Act: 1.4870. Min Act: -0.1700
Data Index: 6074176 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5746. Min Range: -1.5746
Max Act: 1.4342. Min Act: -0.1699
Data Index: 4105286 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5746. Min Range: -1.5746
Max Act: 1.3990. Min Act: -0.1699
Data Index: 2272510 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5746. Min Range: -1.5746
Max Act: 1.4166. Min Act: -0.1700
Data Index: 5288644 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5746. Min Range: -1.5746
Max Act: 1.3990. Min Act: -0.1700
Data Index: 6063554 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5746. Min Range: -1.5746
Max Act: 1.3637. Min Act: -0.1700
Data Index: 351599 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5746. Min Range: -1.5746
Max Act: 1.3637. Min Act: -0.1700
Data Index: 392636 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5746. Min Range: -1.5746
Max Act: 1.3637. Min Act: -0.1699
Data Index: 822672 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5746. Min Range: -1.5746
Max Act: 1.3814. Min Act: -0.1700
Data Index: 5288643 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5746. Min Range: -1.5746
Max Act: 1.3637. Min Act: -0.1699
Data Index: 6063555 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5746. Min Range: -1.5746
Max Act: 1.3461. Min Act: -0.1698
Data Index: 6795421 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5746. Min Range: -1.5746
Max Act: 1.3461. Min Act: -0.1696
Data Index: 1048174 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5746. Min Range: -1.5746
Max Act: 1.3461. Min Act: -0.1700
Data Index: 1783565 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5746. Min Range: -1.5746
Max Act: 1.3461. Min Act: -0.1700
Data Index: 2034792 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5746. Min Range: -1.5746
Max Act: 1.3108. Min Act: -0.1699
Data Index: 6411382 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5746. Min Range: -1.5746
Max Act: 1.3108. Min Act: -0.1700
Data Index: 2034794 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5746. Min Range: -1.5746
Max Act: 1.3108. Min Act: -0.1700
Data Index: 4431056 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5746. Min Range: -1.5746
Max Act: 1.2932. Min Act: -0.1688
Data Index: 1239889 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5746. Min Range: -1.5746
Max Act: 1.2932. Min Act: -0.1700
Data Index: 2272509 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19