Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1926 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8139. Min Range: -6.8139
Max Act: 6.8139. Min Act: -0.1700
Data Index: 5327847 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8139. Min Range: -6.8139
Max Act: 6.6889. Min Act: -0.1700
Data Index: 4951024 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8139. Min Range: -6.8139
Max Act: 6.6889. Min Act: -0.1700
Data Index: 5751967 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8139. Min Range: -6.8139
Max Act: 6.6264. Min Act: -0.1700
Data Index: 7160262 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8139. Min Range: -6.8139
Max Act: 6.5952. Min Act: -0.1700
Data Index: 2176586 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8139. Min Range: -6.8139
Max Act: 6.5639. Min Act: -0.1700
Data Index: 822470 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8139. Min Range: -6.8139
Max Act: 6.5952. Min Act: -0.1700
Data Index: 6975216 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8139. Min Range: -6.8139
Max Act: 6.5639. Min Act: -0.1700
Data Index: 5724727 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8139. Min Range: -6.8139
Max Act: 6.5327. Min Act: -0.1700
Data Index: 4632746 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8139. Min Range: -6.8139
Max Act: 6.5639. Min Act: -0.1700
Data Index: 109554 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8139. Min Range: -6.8139
Max Act: 6.5639. Min Act: -0.1700
Data Index: 7874174 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8139. Min Range: -6.8139
Max Act: 6.4702. Min Act: -0.1700
Data Index: 2807740 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8139. Min Range: -6.8139
Max Act: 6.5014. Min Act: -0.1700
Data Index: 6601527 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8139. Min Range: -6.8139
Max Act: 6.4702. Min Act: -0.1700
Data Index: 1688718 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8139. Min Range: -6.8139
Max Act: 6.4702. Min Act: -0.1700
Data Index: 6274270 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8139. Min Range: -6.8139
Max Act: 6.4389. Min Act: -0.1700
Data Index: 3046295 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8139. Min Range: -6.8139
Max Act: 6.4077. Min Act: -0.1700
Data Index: 3367028 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8139. Min Range: -6.8139
Max Act: 6.4077. Min Act: -0.1700
Data Index: 2807743 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8139. Min Range: -6.8139
Max Act: 6.3764. Min Act: -0.1700
Data Index: 7055627 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8139. Min Range: -6.8139
Max Act: 6.3764. Min Act: -0.1700
Data Index: 4038991 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19