Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3536 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9812. Min Range: -6.9812
Max Act: 6.9812. Min Act: -0.1700
Data Index: 1629908 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9812. Min Range: -6.9812
Max Act: 6.8874. Min Act: -0.1700
Data Index: 4440090 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9812. Min Range: -6.9812
Max Act: 6.7937. Min Act: -0.1700
Data Index: 4656818 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9812. Min Range: -6.9812
Max Act: 6.7937. Min Act: -0.1700
Data Index: 5025666 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9812. Min Range: -6.9812
Max Act: 6.6687. Min Act: -0.1700
Data Index: 3940112 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9812. Min Range: -6.9812
Max Act: 6.6999. Min Act: -0.1700
Data Index: 1868739 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9812. Min Range: -6.9812
Max Act: 6.6374. Min Act: -0.1700
Data Index: 5349049 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9812. Min Range: -6.9812
Max Act: 6.6374. Min Act: -0.1699
Data Index: 7578346 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9812. Min Range: -6.9812
Max Act: 6.6062. Min Act: -0.1700
Data Index: 8177099 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9812. Min Range: -6.9812
Max Act: 6.6062. Min Act: -0.1700
Data Index: 5949074 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9812. Min Range: -6.9812
Max Act: 6.5749. Min Act: -0.1700
Data Index: 3137164 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9812. Min Range: -6.9812
Max Act: 6.4812. Min Act: -0.1700
Data Index: 8635111 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9812. Min Range: -6.9812
Max Act: 6.4499. Min Act: -0.1700
Data Index: 8526569 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9812. Min Range: -6.9812
Max Act: 6.4499. Min Act: -0.1700
Data Index: 7935427 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9812. Min Range: -6.9812
Max Act: 6.4499. Min Act: -0.1700
Data Index: 2727231 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9812. Min Range: -6.9812
Max Act: 6.4187. Min Act: -0.1700
Data Index: 1305013 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9812. Min Range: -6.9812
Max Act: 6.4187. Min Act: -0.1700
Data Index: 2166795 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9812. Min Range: -6.9812
Max Act: 6.4187. Min Act: -0.1700
Data Index: 4656820 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9812. Min Range: -6.9812
Max Act: 6.4187. Min Act: -0.1700
Data Index: 2763473 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9812. Min Range: -6.9812
Max Act: 6.3874. Min Act: -0.1700
Data Index: 4611797 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #19