Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3330 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7051. Min Range: -7.7051
Max Act: 7.7051. Min Act: -0.1700
Data Index: 4356435 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7051. Min Range: -7.7051
Max Act: 7.5801. Min Act: -0.1700
Data Index: 5565413 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7051. Min Range: -7.7051
Max Act: 7.4863. Min Act: -0.1700
Data Index: 4172571 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7051. Min Range: -7.7051
Max Act: 7.4551. Min Act: -0.1700
Data Index: 4048087 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7051. Min Range: -7.7051
Max Act: 7.4238. Min Act: -0.1700
Data Index: 1572923 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7051. Min Range: -7.7051
Max Act: 7.3926. Min Act: -0.1700
Data Index: 6737434 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7051. Min Range: -7.7051
Max Act: 7.3613. Min Act: -0.1700
Data Index: 8249357 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7051. Min Range: -7.7051
Max Act: 7.3613. Min Act: -0.1700
Data Index: 8127207 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7051. Min Range: -7.7051
Max Act: 7.3613. Min Act: -0.1700
Data Index: 886068 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7051. Min Range: -7.7051
Max Act: 7.3301. Min Act: -0.1700
Data Index: 4341557 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7051. Min Range: -7.7051
Max Act: 7.3301. Min Act: -0.1700
Data Index: 1386617 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7051. Min Range: -7.7051
Max Act: 7.3301. Min Act: -0.1700
Data Index: 3087367 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7051. Min Range: -7.7051
Max Act: 7.3301. Min Act: -0.1700
Data Index: 1134250 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7051. Min Range: -7.7051
Max Act: 7.3301. Min Act: -0.1700
Data Index: 437311 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7051. Min Range: -7.7051
Max Act: 7.2988. Min Act: -0.1700
Data Index: 4092389 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7051. Min Range: -7.7051
Max Act: 7.2988. Min Act: -0.1700
Data Index: 3794788 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7051. Min Range: -7.7051
Max Act: 7.2988. Min Act: -0.1700
Data Index: 6629592 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7051. Min Range: -7.7051
Max Act: 7.2363. Min Act: -0.1700
Data Index: 6172265 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7051. Min Range: -7.7051
Max Act: 7.2363. Min Act: -0.1700
Data Index: 834868 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7051. Min Range: -7.7051
Max Act: 7.2051. Min Act: -0.1700
Data Index: 4849077 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19