Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8455. Min Range: -3.8455
Max Act: 3.8455. Min Act: -0.1700
Data Index: 45183 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8455. Min Range: -3.8455
Max Act: 3.7829. Min Act: -0.1700
Data Index: 5611653 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8455. Min Range: -3.8455
Max Act: 3.7204. Min Act: -0.1700
Data Index: 5998363 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8455. Min Range: -3.8455
Max Act: 3.6891. Min Act: -0.1700
Data Index: 3890475 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8455. Min Range: -3.8455
Max Act: 3.6578. Min Act: -0.1700
Data Index: 3720760 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8455. Min Range: -3.8455
Max Act: 3.6891. Min Act: -0.1700
Data Index: 4954984 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8455. Min Range: -3.8455
Max Act: 3.6578. Min Act: -0.1700
Data Index: 45179 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8455. Min Range: -3.8455
Max Act: 3.6578. Min Act: -0.1700
Data Index: 5443086 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8455. Min Range: -3.8455
Max Act: 3.6265. Min Act: -0.1700
Data Index: 7796113 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8455. Min Range: -3.8455
Max Act: 3.6265. Min Act: -0.1700
Data Index: 895369 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8455. Min Range: -3.8455
Max Act: 3.5952. Min Act: -0.1700
Data Index: 4385495 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8455. Min Range: -3.8455
Max Act: 3.5952. Min Act: -0.1700
Data Index: 1363053 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8455. Min Range: -3.8455
Max Act: 3.5639. Min Act: -0.1700
Data Index: 5812446 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8455. Min Range: -3.8455
Max Act: 3.5952. Min Act: -0.1700
Data Index: 8479923 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8455. Min Range: -3.8455
Max Act: 3.5952. Min Act: -0.1700
Data Index: 8291442 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8455. Min Range: -3.8455
Max Act: 3.5952. Min Act: -0.1700
Data Index: 4632124 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8455. Min Range: -3.8455
Max Act: 3.5639. Min Act: -0.1700
Data Index: 2810565 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8455. Min Range: -3.8455
Max Act: 3.5639. Min Act: -0.1700
Data Index: 7140514 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8455. Min Range: -3.8455
Max Act: 3.5639. Min Act: -0.1700
Data Index: 2785143 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8455. Min Range: -3.8455
Max Act: 3.5639. Min Act: -0.1700
Data Index: 4632125 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19