Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3305 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4001. Min Range: -4.4001
Max Act: 4.4001. Min Act: -0.1700
Data Index: 4872313 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4001. Min Range: -4.4001
Max Act: 4.0563. Min Act: -0.1700
Data Index: 2551690 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4001. Min Range: -4.4001
Max Act: 4.0563. Min Act: -0.1700
Data Index: 1961334 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4001. Min Range: -4.4001
Max Act: 4.0251. Min Act: -0.1700
Data Index: 5044178 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4001. Min Range: -4.4001
Max Act: 4.0251. Min Act: -0.1700
Data Index: 4500739 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4001. Min Range: -4.4001
Max Act: 3.9938. Min Act: -0.1700
Data Index: 8297247 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4001. Min Range: -4.4001
Max Act: 3.9938. Min Act: -0.1700
Data Index: 4528699 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4001. Min Range: -4.4001
Max Act: 3.9938. Min Act: -0.1700
Data Index: 4018869 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4001. Min Range: -4.4001
Max Act: 3.9938. Min Act: -0.1700
Data Index: 5829337 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4001. Min Range: -4.4001
Max Act: 3.9938. Min Act: -0.1700
Data Index: 786814 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4001. Min Range: -4.4001
Max Act: 3.9625. Min Act: -0.1700
Data Index: 8411352 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4001. Min Range: -4.4001
Max Act: 3.9625. Min Act: -0.1700
Data Index: 1242274 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4001. Min Range: -4.4001
Max Act: 3.9313. Min Act: -0.1700
Data Index: 660924 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4001. Min Range: -4.4001
Max Act: 3.9625. Min Act: -0.1700
Data Index: 4574714 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4001. Min Range: -4.4001
Max Act: 3.9313. Min Act: -0.1700
Data Index: 6669484 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4001. Min Range: -4.4001
Max Act: 3.9000. Min Act: -0.1700
Data Index: 6734869 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4001. Min Range: -4.4001
Max Act: 3.9313. Min Act: -0.1700
Data Index: 4136748 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4001. Min Range: -4.4001
Max Act: 3.9313. Min Act: -0.1700
Data Index: 2551694 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4001. Min Range: -4.4001
Max Act: 3.9000. Min Act: -0.1700
Data Index: 271982 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4001. Min Range: -4.4001
Max Act: 3.9313. Min Act: -0.1700
Data Index: 5518231 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19