Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3343 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1887. Min Range: -7.1887
Max Act: 7.1887. Min Act: -0.1700
Data Index: 4713374 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1887. Min Range: -7.1887
Max Act: 6.9387. Min Act: -0.1700
Data Index: 2900442 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1887. Min Range: -7.1887
Max Act: 6.9075. Min Act: -0.1700
Data Index: 3579637 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1887. Min Range: -7.1887
Max Act: 6.8762. Min Act: -0.1700
Data Index: 1850978 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1887. Min Range: -7.1887
Max Act: 6.8762. Min Act: -0.1700
Data Index: 8587935 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1887. Min Range: -7.1887
Max Act: 6.8137. Min Act: -0.1700
Data Index: 8555984 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1887. Min Range: -7.1887
Max Act: 6.8137. Min Act: -0.1700
Data Index: 4671443 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1887. Min Range: -7.1887
Max Act: 6.8137. Min Act: -0.1700
Data Index: 2529530 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1887. Min Range: -7.1887
Max Act: 6.7512. Min Act: -0.1700
Data Index: 1199042 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1887. Min Range: -7.1887
Max Act: 6.7512. Min Act: -0.1700
Data Index: 8407439 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1887. Min Range: -7.1887
Max Act: 6.6887. Min Act: -0.1700
Data Index: 5327102 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1887. Min Range: -7.1887
Max Act: 6.6575. Min Act: -0.1700
Data Index: 1440418 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1887. Min Range: -7.1887
Max Act: 6.6575. Min Act: -0.1700
Data Index: 752048 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1887. Min Range: -7.1887
Max Act: 6.5950. Min Act: -0.1700
Data Index: 732142 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1887. Min Range: -7.1887
Max Act: 6.5950. Min Act: -0.1700
Data Index: 502640 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1887. Min Range: -7.1887
Max Act: 6.5950. Min Act: -0.1700
Data Index: 8655963 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1887. Min Range: -7.1887
Max Act: 6.5950. Min Act: -0.1700
Data Index: 5985417 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1887. Min Range: -7.1887
Max Act: 6.5950. Min Act: -0.1700
Data Index: 3791614 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1887. Min Range: -7.1887
Max Act: 6.5637. Min Act: -0.1700
Data Index: 1250745 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1887. Min Range: -7.1887
Max Act: 6.5637. Min Act: -0.1700
Data Index: 1904479 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19