Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6380 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8889. Min Range: -7.8889
Max Act: 7.8889. Min Act: -0.1700
Data Index: 147735 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8889. Min Range: -7.8889
Max Act: 7.6389. Min Act: -0.1700
Data Index: 7919609 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8889. Min Range: -7.8889
Max Act: 7.3264. Min Act: -0.1700
Data Index: 1034316 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8889. Min Range: -7.8889
Max Act: 7.1077. Min Act: -0.1700
Data Index: 6634312 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8889. Min Range: -7.8889
Max Act: 7.0764. Min Act: -0.1700
Data Index: 7016548 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8889. Min Range: -7.8889
Max Act: 6.9827. Min Act: -0.1700
Data Index: 1610920 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8889. Min Range: -7.8889
Max Act: 6.9827. Min Act: -0.1700
Data Index: 8504294 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8889. Min Range: -7.8889
Max Act: 6.8889. Min Act: -0.1700
Data Index: 4385668 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8889. Min Range: -7.8889
Max Act: 6.8889. Min Act: -0.1700
Data Index: 3746785 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8889. Min Range: -7.8889
Max Act: 6.8264. Min Act: -0.1700
Data Index: 7857355 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8889. Min Range: -7.8889
Max Act: 6.8577. Min Act: -0.1700
Data Index: 1725104 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8889. Min Range: -7.8889
Max Act: 6.8577. Min Act: -0.1700
Data Index: 2923237 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8889. Min Range: -7.8889
Max Act: 6.8577. Min Act: -0.1700
Data Index: 3216123 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8889. Min Range: -7.8889
Max Act: 6.7952. Min Act: -0.1700
Data Index: 8088633 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8889. Min Range: -7.8889
Max Act: 6.7639. Min Act: -0.1700
Data Index: 6443085 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8889. Min Range: -7.8889
Max Act: 6.7639. Min Act: -0.1700
Data Index: 1991034 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8889. Min Range: -7.8889
Max Act: 6.7639. Min Act: -0.1700
Data Index: 2206355 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8889. Min Range: -7.8889
Max Act: 6.7327. Min Act: -0.1700
Data Index: 431282 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8889. Min Range: -7.8889
Max Act: 6.6702. Min Act: -0.1700
Data Index: 1592058 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8889. Min Range: -7.8889
Max Act: 6.7014. Min Act: -0.1700
Data Index: 32112 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19