Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 52 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5800. Min Range: -5.5800
Max Act: 5.5800. Min Act: -0.1700
Data Index: 1885348 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5800. Min Range: -5.5800
Max Act: 5.5175. Min Act: -0.1700
Data Index: 3492824 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5800. Min Range: -5.5800
Max Act: 5.4550. Min Act: -0.1700
Data Index: 5403727 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5800. Min Range: -5.5800
Max Act: 5.4238. Min Act: -0.1700
Data Index: 8515294 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5800. Min Range: -5.5800
Max Act: 5.3925. Min Act: -0.1700
Data Index: 5209893 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5800. Min Range: -5.5800
Max Act: 5.3925. Min Act: -0.1700
Data Index: 4927682 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5800. Min Range: -5.5800
Max Act: 5.3613. Min Act: -0.1700
Data Index: 4881615 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5800. Min Range: -5.5800
Max Act: 5.3300. Min Act: -0.1700
Data Index: 6899126 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5800. Min Range: -5.5800
Max Act: 5.2988. Min Act: -0.1700
Data Index: 1920450 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5800. Min Range: -5.5800
Max Act: 5.3300. Min Act: -0.1700
Data Index: 3897130 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5800. Min Range: -5.5800
Max Act: 5.2988. Min Act: -0.1700
Data Index: 566425 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5800. Min Range: -5.5800
Max Act: 5.2988. Min Act: -0.1700
Data Index: 188235 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5800. Min Range: -5.5800
Max Act: 5.2988. Min Act: -0.1700
Data Index: 6242897 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5800. Min Range: -5.5800
Max Act: 5.2675. Min Act: -0.1700
Data Index: 7277405 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5800. Min Range: -5.5800
Max Act: 5.2675. Min Act: -0.1700
Data Index: 3536091 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5800. Min Range: -5.5800
Max Act: 5.2675. Min Act: -0.1700
Data Index: 7305050 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5800. Min Range: -5.5800
Max Act: 5.2363. Min Act: -0.1700
Data Index: 3261115 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5800. Min Range: -5.5800
Max Act: 5.2675. Min Act: -0.1700
Data Index: 3057306 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5800. Min Range: -5.5800
Max Act: 5.2675. Min Act: -0.1700
Data Index: 2469645 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5800. Min Range: -5.5800
Max Act: 5.2988. Min Act: -0.1700
Data Index: 5669811 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19